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

Annotations only declare idempotentHint=true and destructiveHint=false. The description adds the login requirement (需要登录), the key behavioral detail that the need stays visible in search, the 1–90 day bound with a 7-day default, and the reversibility path through the preferenceId receipt with a fallback lookup. That is meaningful context beyond what the annotations convey.

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?

The single dense paragraph front-loads the login requirement and the action, then stacks alternatives and the rollback path with arrow notation. Every clause carries information, but the telegraphic style (list_my_needs→暂停) is slightly hard to parse on first read compared with plain sentences.

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 two-parameter mutation with no output schema, the description covers the auth prerequisite, the exact effect and its limits, the fact that visibility is unaffected, the receipt needed to undo the pause early, and how to get that receipt if absent. Nothing an agent needs in order to call it correctly and reverse it is missing.

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 100%, so needId and days (with 1–90 min/max and default 7) are already documented in the schema. The description restates that needId comes from list_my_needs and adds no new meaning about the days semantics (for example, whether the pause counts calendar days or resets on change). Baseline 3 is appropriate when the schema does the heavy lifting.

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 states a specific verb and object: temporarily suspend auto-icebreak (自动破冰) for the user's own published need, from 1 to 90 days, default 7, and explicitly notes that the need is not hidden from search. It also names the sibling that handles the neighboring case (unpublish_need for hiding, snooze/icebreak=false for global), so the agent can distinguish this tool from close 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?

It gives a concrete precondition (list_my_needs → pause) plus two explicit exclusions: use snooze/icebreak=false for a global pause and unpublish_need to hide the need. It also describes how to recover early via revoke_my_match_preference with the preferenceId receipt, and what to do when that receipt is missing (list_my_match_preferences).

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