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

With only readOnlyHint=false available, the description carries real weight by disclosing the confirm-gate: it previews unless confirm is true. That is exactly the kind of behavioral trait annotations cannot express. It does not say whether requeue discards prior run output, consumes AI credits, or is reversible, leaving mutation side effects unclear.

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?

Two compact sentences with the action front-loaded and the gating caveat parenthesized where it is easy to catch. No wasted text, though 'for the client' adds little precision.

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 mutation tool with no output schema, the confirm-gate is covered but the post-execution picture is not: no statement about what the preview returns, what happens to the original run record, or any authorization requirement on runId. Adequate but with clear gaps.

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 coverage is 50%: confirm is fully documented in the schema, so the description's parenthetical is largely redundant, while runId has no schema description and gets only the indirect hint that it refers to a failed/rejected run. The description does not compensate for the undocumented parameter.

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 ('Re-run') and a precisely scoped resource ('a failed or rejected AI coaching run for the client'), which implicitly distinguishes it from trigger_ai_coach_run and approve_ai_run. It stops short of naming those siblings explicitly, so the differentiation is inferential rather than stated.

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?

The precondition ('failed or rejected' run) tells the agent when this tool applies, but nothing says where a qualifying runId comes from (e.g. list_ai_runs_awaiting_review) or when to prefer approve_ai_run / trigger_ai_coach_run instead. Usage is implied, not guided.

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