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

Annotations already declare idempotentHint=true and destructiveHint=false, so the description's 'identical retries keep the same revision' mainly reinforces that. The genuinely additive detail is the optimistic-concurrency contract: a changed answer requires expectedRevision from a previous read, which is not derivable from the annotations.

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 short sentences, each carrying distinct information: what it does, the retry contract, and the revision precondition. Front-loaded with the action and zero filler.

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?

The presence of an output schema means return values need no explanation, and annotations cover the safety profile. However, for a 6-parameter mutation with no schema descriptions, the description leaves key semantics (notably what RETIRED does and whether it removes or archives the answer) unaddressed.

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 0% across 6 parameters, so the description carries the full burden — but it only explains expectedRevision. It never clarifies status (APPROVED vs RETIRED), what deskId scopes, or the length constraints on topic/question/answer, leaving most parameters undocumented anywhere.

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?

The description names a specific verb pair (store/revise) and resource (an approved answer), and the 'explicitly approved' qualifier distinguishes it from the read-oriented sibling search_approved_answers. It does not explicitly distinguish itself from save_approved_commitment, but the resource noun is clear enough to route correctly.

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?

It states the precondition for use (the user has explicitly approved the answer) and gives a concrete conditional rule: a changed answer requires expectedRevision from a prior read. What is missing is an explicit pointer to alternatives (e.g., search_approved_answers for reads), so it falls 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.