jeff.agents.tool-routev1.4.0

Agent tool selection from a menu

Selects the next tool from a menu included in the request, using the conversation for context. Can also indicate that no tool is needed or that the user must supply missing information.

Open in playground

Example

Context

app: Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices and clients and emails invoices on request.
today: Monday 2 November 2026
tools: def find_invoice(client: str, month: str) -> dict: """Finds the studio's invoice for a client and month.""" def send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict: """Emails an invoice to a recipient, with optional copies.""" def create_invoice(client: str, items: list[dict]) -> dict: """Creates a new draft invoice."""
conversation: - {"role":"user","content":"Morning! Can you send the October invoice for Orbit Print?"} - {"role":"assistant","content":"I found it, INV-2026-0412 for 2,350.00, still unpaid. Who at Orbit Print should receive it?"}

Input

Send it to their accounts address, accounts@orbitprint.example, and copy me.

Labels (the options)

find_invoice: Finds the studio's invoice for a client and month.
send_invoice: Emails an invoice to a recipient, with optional copies.
create_invoice: Creates a new draft invoice.
none: No tool is needed, or no tool on the menu can do what the user asks.
ask_user: A tool fits, but a required detail is missing and the agent must ask the user.

Answer (JSON)

value send_invoice, confidence 0.998

Top options

send_invoice 0.998
ask_user 0.002
find_invoice 0

The user has given the last detail the agent needed, so the next tool to call is send_invoice.

Open in playground

import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client:     decide = client.function("jeff.agents.tool-route.tool", context={        "app": "Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices and clients and emails invoices on request.",        "today": "Monday 2 November 2026",        "tools": "def find_invoice(client: str, month: str) -> dict:\n    \"\"\"Finds the studio's invoice for a client and month.\"\"\"\ndef send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict:\n    \"\"\"Emails an invoice to a recipient, with optional copies.\"\"\"\ndef create_invoice(client: str, items: list[dict]) -> dict:\n    \"\"\"Creates a new draft invoice.\"\"\"",        "conversation": [            {                "role": "user",                "content": "Morning! Can you send the October invoice for Orbit Print?",            },            {                "role": "assistant",                "content": "I found it, INV-2026-0412 for 2,350.00, still unpaid. Who at Orbit Print should receive it?",            },        ],    }, labels={        "find_invoice": "Finds the studio's invoice for a client and month.",        "send_invoice": "Emails an invoice to a recipient, with optional copies.",        "create_invoice": "Creates a new draft invoice.",        "none": "No tool is needed, or no tool on the menu can do what the user asks.",        "ask_user": "A tool fits, but a required detail is missing and the agent must ask the user.",    })     decision = decide("Send it to their accounts address, accounts@orbitprint.example, and copy me.")     print(decision.value, decision.confidence)

More examples

Look up an invoicefind_invoice · 0.811

Context

app: Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices, clients and supplier bills, emails invoices and pays bills on request.
today: Monday 2 November 2026
tools: def find_invoice(client: str, month: str) -> dict: """Finds the studio's invoice for a client and month.""" def send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict: """Emails an invoice to a recipient, with optional copies.""" def create_invoice(client: str, items: list[dict]) -> dict: """Creates a new draft invoice."""
conversation

Input

How much did we bill Moss & Gale in September 2026?

Labels (the options)

find_invoice: Finds the studio's invoice for a client and month.
send_invoice: Emails an invoice to a recipient, with optional copies.
create_invoice: Creates a new draft invoice.
none: No tool is needed, or no tool on the menu can do what the user asks.
ask_user: A tool fits, but a required detail is missing and the agent must ask the user.

Answer (JSON)

value find_invoice, confidence 0.811

Top options

find_invoice 0.811
none 0.166
ask_user 0.018

The user asks what was billed to a client in a given month, so the tool to call is find_invoice.

Open in playground

import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client:     decide = client.function("jeff.agents.tool-route.tool", context={        "app": "Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices, clients and supplier bills, emails invoices and pays bills on request.",        "today": "Monday 2 November 2026",        "tools": "def find_invoice(client: str, month: str) -> dict:\n    \"\"\"Finds the studio's invoice for a client and month.\"\"\"\ndef send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict:\n    \"\"\"Emails an invoice to a recipient, with optional copies.\"\"\"\ndef create_invoice(client: str, items: list[dict]) -> dict:\n    \"\"\"Creates a new draft invoice.\"\"\"",        "conversation": [],    }, labels={        "find_invoice": "Finds the studio's invoice for a client and month.",        "send_invoice": "Emails an invoice to a recipient, with optional copies.",        "create_invoice": "Creates a new draft invoice.",        "none": "No tool is needed, or no tool on the menu can do what the user asks.",        "ask_user": "A tool fits, but a required detail is missing and the agent must ask the user.",    })     decision = decide("How much did we bill Moss & Gale in September 2026?")     print(decision.value, decision.confidence)

Send an invoice, but which one?ask_user · 0.991

Context

app: Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices, clients and supplier bills, emails invoices and pays bills on request.
today: Monday 2 November 2026
tools: def find_invoice(client: str, month: str) -> dict: """Finds the studio's invoice for a client and month.""" def send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict: """Emails an invoice to a recipient, with optional copies.""" def create_invoice(client: str, items: list[dict]) -> dict: """Creates a new draft invoice."""
conversation

Input

Send the invoice to the client, please.

Labels (the options)

find_invoice: Finds the studio's invoice for a client and month.
send_invoice: Emails an invoice to a recipient, with optional copies.
create_invoice: Creates a new draft invoice.
none: No tool is needed, or no tool on the menu can do what the user asks.
ask_user: A tool fits, but a required detail is missing and the agent must ask the user.

Answer (JSON)

value ask_user, confidence 0.991

Top options

ask_user 0.991
send_invoice 0.004
find_invoice 0.002

The user wants an invoice sent but names neither the invoice nor the client, so the agent must ask_user.

Open in playground

import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client:     decide = client.function("jeff.agents.tool-route.tool", context={        "app": "Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices, clients and supplier bills, emails invoices and pays bills on request.",        "today": "Monday 2 November 2026",        "tools": "def find_invoice(client: str, month: str) -> dict:\n    \"\"\"Finds the studio's invoice for a client and month.\"\"\"\ndef send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict:\n    \"\"\"Emails an invoice to a recipient, with optional copies.\"\"\"\ndef create_invoice(client: str, items: list[dict]) -> dict:\n    \"\"\"Creates a new draft invoice.\"\"\"",        "conversation": [],    }, labels={        "find_invoice": "Finds the studio's invoice for a client and month.",        "send_invoice": "Emails an invoice to a recipient, with optional copies.",        "create_invoice": "Creates a new draft invoice.",        "none": "No tool is needed, or no tool on the menu can do what the user asks.",        "ask_user": "A tool fits, but a required detail is missing and the agent must ask the user.",    })     decision = decide("Send the invoice to the client, please.")     print(decision.value, decision.confidence)

The user says thanksnone · 1

Context

app: Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices, clients and supplier bills, emails invoices and pays bills on request.
today: Monday 2 November 2026
tools: def find_invoice(client: str, month: str) -> dict: """Finds the studio's invoice for a client and month.""" def send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict: """Emails an invoice to a recipient, with optional copies.""" def create_invoice(client: str, items: list[dict]) -> dict: """Creates a new draft invoice."""
conversation: - {"role":"user","content":"Send the October invoice for Orbit Print to accounts@orbitprint.example."} - {"role":"assistant","content":"Done, INV-2026-0412 has been sent to accounts@orbitprint.example."}

Input

Perfect, thank you!

Labels (the options)

find_invoice: Finds the studio's invoice for a client and month.
send_invoice: Emails an invoice to a recipient, with optional copies.
create_invoice: Creates a new draft invoice.
none: No tool is needed, or no tool on the menu can do what the user asks.
ask_user: A tool fits, but a required detail is missing and the agent must ask the user.

Answer (JSON)

value none, confidence 1

Top options

none 1
ask_user 0
send_invoice 0

The user is only saying thank you, so no tool is needed and the answer is none.

Open in playground

import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client:     decide = client.function("jeff.agents.tool-route.tool", context={        "app": "Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices, clients and supplier bills, emails invoices and pays bills on request.",        "today": "Monday 2 November 2026",        "tools": "def find_invoice(client: str, month: str) -> dict:\n    \"\"\"Finds the studio's invoice for a client and month.\"\"\"\ndef send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict:\n    \"\"\"Emails an invoice to a recipient, with optional copies.\"\"\"\ndef create_invoice(client: str, items: list[dict]) -> dict:\n    \"\"\"Creates a new draft invoice.\"\"\"",        "conversation": [            {                "role": "user",                "content": "Send the October invoice for Orbit Print to accounts@orbitprint.example.",            },            {                "role": "assistant",                "content": "Done, INV-2026-0412 has been sent to accounts@orbitprint.example.",            },        ],    }, labels={        "find_invoice": "Finds the studio's invoice for a client and month.",        "send_invoice": "Emails an invoice to a recipient, with optional copies.",        "create_invoice": "Creates a new draft invoice.",        "none": "No tool is needed, or no tool on the menu can do what the user asks.",        "ask_user": "A tool fits, but a required detail is missing and the agent must ask the user.",    })     decision = decide("Perfect, thank you!")     print(decision.value, decision.confidence)

Draft a new invoice with its itemscreate_invoice · 0.821

Context

app: Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices, clients and supplier bills, emails invoices and pays bills on request.
today: Monday 2 November 2026
tools: def find_invoice(client: str, month: str) -> dict: """Finds the studio's invoice for a client and month.""" def send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict: """Emails an invoice to a recipient, with optional copies.""" def create_invoice(client: str, items: list[dict]) -> dict: """Creates a new draft invoice."""
conversation

Input

Make a new invoice for Harbour Lane Cafe for the menu design, 2 days at 450.00 a day.

Labels (the options)

find_invoice: Finds the studio's invoice for a client and month.
send_invoice: Emails an invoice to a recipient, with optional copies.
create_invoice: Creates a new draft invoice.
none: No tool is needed, or no tool on the menu can do what the user asks.
ask_user: A tool fits, but a required detail is missing and the agent must ask the user.

Answer (JSON)

value create_invoice, confidence 0.821

Top options

create_invoice 0.821
ask_user 0.168
none 0.006

The user gives the client, the work and the price for a new invoice, so the tool to call is create_invoice.

Open in playground

import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client:     decide = client.function("jeff.agents.tool-route.tool", context={        "app": "Pinecrest Books, a bookkeeping assistant for a small design studio. It keeps the studio's invoices, clients and supplier bills, emails invoices and pays bills on request.",        "today": "Monday 2 November 2026",        "tools": "def find_invoice(client: str, month: str) -> dict:\n    \"\"\"Finds the studio's invoice for a client and month.\"\"\"\ndef send_invoice(invoice_id: str, to: str, cc: list[str] = []) -> dict:\n    \"\"\"Emails an invoice to a recipient, with optional copies.\"\"\"\ndef create_invoice(client: str, items: list[dict]) -> dict:\n    \"\"\"Creates a new draft invoice.\"\"\"",        "conversation": [],    }, labels={        "find_invoice": "Finds the studio's invoice for a client and month.",        "send_invoice": "Emails an invoice to a recipient, with optional copies.",        "create_invoice": "Creates a new draft invoice.",        "none": "No tool is needed, or no tool on the menu can do what the user asks.",        "ask_user": "A tool fits, but a required detail is missing and the agent must ask the user.",    })     decision = decide("Make a new invoice for Harbour Lane Cafe for the menu design, 2 days at 450.00 a day.")     print(decision.value, decision.confidence)

Use when

Your tool menu is supplied as text, function signatures or schemas in the request.
You need a tool-selection decision with a probability.

Avoid when

You need to generate tool arguments; this adapter selects a tool without constructing the call.

Context and input

Field	Kind	Description
request	input	The user's latest message.
app	context	The application the agent works in: its name and a description of what it does and for whom.
today	context	Today's date, written out (for example 'Wednesday 23 June 2027').
tools	context	The tool menu, in any common format (Python signatures, JSON schemas and so on).
conversation	context	The conversation so far, a list of messages (user, assistant, tool calls and tool results).

Functions

Key	Interface	Instructions	Labels
tool	route	What should the agent do next with the user's latest message? Choose the tool on the menu that should be called now when that tool can do what the user asks and the request and the conversation give every detail it requires (details the agent can take from earlier in the conversation count). Choose none when no tool is needed or none fits: the user is chatting or thanking, asks something the conversation already answers, or asks for something no tool on the menu can do. Choose ask_user when a tool fits but a required detail is missing and cannot be taken from the conversation, or when the request could mean two different records or actions and the agent must ask which. Read the tool names and descriptions carefully: similar tools do different things.	from the caller

How it was measured

Test accuracy: the share of test rows whose top answer was right.

71.6% on When2Call, a public function-calling benchmark (questions and tools from the Berkeley Function Calling Leaderboard) (3,646 rows). public benchmark
98.2% on the in-house test (2,000 rows). in-house: same generator as the training data
96.7% on a second in-house test of unseen cases (2,000 rows). in-house: same generator as the training data

When confident

From the calibration set: at or above the threshold confidence, how often the answer is right, and how often the adapter is that confident. Below it, escalate.

Function	Right when confident	Confident on	Threshold	Calibration rows
tool	98.5%	100.0%	0.41	2,000

Base: Jeff v1.4. Adapter trained: 25 October 2026.

Base

jeff-base v1.4

Call it

jeff.agents.tool-route.tool, with placeholders for its input and context.

import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client:     decide = client.function("jeff.agents.tool-route.tool", context={        "app": "<app>",        "today": "<today>",        "tools": "<tools>",        "conversation": "<conversation>",    })     decision = decide("<request>")     print(decision.value, decision.confidence)

Download

Weights: mstrasser/jeff-adapter-tool-route (v1.4)

Licence: Apache-2.0