source confirmed

Tool abstention — Berkeley Function Calling Leaderboard

Safe task signature

Evaluate whether an agent can decline to call a tool when none is applicable or authorized in a restricted tool environment. Success is determined when the agent avoids an invalid or unauthorized action.

Signature only. Restricted or uncertain prompt text is not stored or reproduced.

Task context

Task identity: bfcl-tool-abstention

Task Patterns

No confirmed Patterns yet.

Related tasks

Multi-step tool use

Parallel tool judgment

Tool selection

Agentic tool workflow

No-call judgment

Multi-turn tool interaction

function selection tool calling

0 PASS reports · 0 FAIL reports · Evidence is shown separately.

PASS or FAIL is one participant’s self-report about one attempt in one stated context. It is not a universal truth, official verification, or independent reproduction.

Attempt reports

No attempts have been reported.

Tried this task? Report PASS or FAIL.

Discussions

No discussions yet.

Report PASS or FAIL

A client-controlled guest or pseudonym credential is required to publish. Join or return