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

Annotations only provide idempotentHint=true and destructiveHint=false, but the description adds real behavioral facts beyond them: login is required, a soft-failure signal (recorded=false means nothing was written), server-side downgrade of an invalid needId to TEMPORARY scope, and a hard cap of 20 entries with oldest-entry eviction. What it does not cover is the shape of the success response beyond the recorded flag, which keeps it from a 5.

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-loads the login gate and the core action, then packs prerequisites, failure semantics, quota, and alternatives into a few dense clause groups with no filler. The mixed-language tokens ("recorded=false", "scopeDowngraded") and telegraphic punctuation make it terse to the point of being slightly cryptic, costing it a point.

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 5-parameter write tool with no output schema but full schema descriptions, the definition covers the login prerequisite, ordering with the list tool, downgrade behavior, capacity/eviction, and a failure indicator. The main remaining gap is that the exact response fields (beyond recorded) and how eviction interacts with idempotency are not spelled out.

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 the enum meanings for polarity/scope, the days range, and the needId source are already fully documented in the schema. The description only adds the cross-parameter rule that an invalid needId is downgraded to TEMPORARY (also in the schema) and that re-submitting the same entry updates its scope; it adds little parameter meaning beyond the structured fields.

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 the specific action (record a WANT/AVOID match preference) together with upsert semantics ("同条更新范围" – editing the same entry updates its scope), and explicitly names the two sibling tools it is not (pause_need_icebreak for pausing a single need, revoke_my_match_preference for revocation). An agent can distinguish it from those siblings without opening any schema.

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?

Gives an explicit prerequisite workflow ("先list_my_match_preferences" – call the list tool first) and routes the agent to alternatives by naming pause_need_icebreak for pausing one need and revoke_my_match_preference for removal. When-to-use and when-to-use-something-else are both present.

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