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

Adds real context beyond the readOnly/idempotent annotations: requires login, PRIVATE facts are match-only while PUBLIC shows on the profile homepage, capped at 20 entries with oldest-eviction, and stale needs can be cleaned up. These are non-obvious side behaviors. Not 5 because cleanup/eviction mechanics aren't fully reconciled with a read-only tool.

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?

Dense but front-loaded with the login requirement; however the single run-on clause packing category lists and mutation-routing makes it hard to parse and mixes read behavior with setter-tool routing.

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?

No output schema, so the description carries return-value burden — and it does name the preference categories and privacy visibility, plus the 20-item cap. Missing only the response shape (e.g., list vs grouped) to reach 5.

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?

Zero parameters, so baseline is 4; no param meaning to convey. The description instead specifies the output content categories, which is useful.

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 read verb (读/reads) and enumerates the preference categories returned (WANT/AVOID, PROFILE/NEED/TEMP, 节奏/角色/暂停), distinguishing it from the set_/revoke_ siblings it names. Not a 5 because the title/description mix Chinese labels that an agent must map to concept names.

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 routes the agent: use set_my_match_preference / revoke_my_match_preference to modify, and pause_need_icebreak to pause a single need — so an agent knows this is the read-only counterpart. No explicit 'when not to use' beyond that routing.

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