agent_handoff

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does meaningful work: it discloses the LLM-synthesized nature, that handoff context is linked back to the session, the side effect of complete=true marking the session completed, and the hard prerequisite of a configured LLM provider. It omits reversibility of the completed status and any auth/permission needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with what is produced and finished with the prerequisite; the parenthetical content list is information-dense rather than filler. Slightly packed but every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-param, no-annotation, no-output-schema mutation tool, the description covers the artifact produced, the main side effect, and the LLM prerequisite. It does not describe what happens to the returned handoff or how errors surface when no provider is configured, leaving a small gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter (dry_run, project, complete, workspace, since_days, session_id) is already documented in the schema. The description only reiterates complete=true and adds that workspace falls back to the session's workspace implicitly; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Generate a handoff document for the session's workspace') and enumerates contents (TL;DR, in-progress, next-steps, open-questions), so an agent knows exactly what artifact is produced. It does not explicitly differentiate itself from nearby siblings like agent_checkpoint or agent_session_end, which is the only thing keeping it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clear context: call 'at run end', and pass complete=true to additionally close the session. It also states the prerequisite that an LLM provider must be configured. No explicit when-not or named alternative to sibling tools, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.