diana_experience_review

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with 'Changes nothing', while adding genuinely new behavioral context: the output is a set of proposals, and the actual mutation is deferred to diana_experience_update with a specific merge encoding. It does not discuss limits on result volume or how 'repeatedly reported as unhelpful' is determined, but the safety and workflow profile is well covered.

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?

Front-loaded with a one-line purpose before the long enumeration of returned categories, and the trailing 'Args' block is compact. The parenthetical merge instruction is somewhat operational detail that arguably belongs with diana_experience_update, but it is short enough not to bloat the definition.

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 read-only, single-parameter review tool with an output schema, this covers what an agent needs: what is returned, that nothing is mutated, and which tool performs the follow-up. The remaining gaps (return volume, how categories are ranked) are modest given the output schema exists to describe the shape of results.

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 0% and the only parameter is 'limit', which the description documents in a single line ('items per list'). That phrasing carries real meaning the schema lacks — the limit applies per category list rather than globally — which matters given multiple returned lists. Beyond that one clarification it adds nothing about defaults or interaction with the returned groups.

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 and resource ('periodic review of the experience handbook') and immediately enumerates the exact categories of items surfaced (approval-worthy drafts, AI drafts missing a cause, merge candidates, failed/foreign-version verification, repeatedly unhelpful entries). This clearly separates it from sibling list/verify/update tools. Slightly weakened by the vague opening clause 'what to bring to the user', which is less precise than the enumeration that follows.

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?

Explicitly frames this as a propose-then-apply workflow ('Changes nothing: propose each step to the user, then apply it with diana_experience_update') and names the follow-up tool, including the concrete merge convention ('mark the others obsolete with "合并到 <id>"'). It does not state when to run a review versus simply calling diana_experience_list, but the alternative tool for applying changes is named unambiguously.

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