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

Annotations only declare destructiveHint=false, and the description adds the material behavior the agent actually needs: auth requirement, that preview is the default mode, that a cryptographic previewHash must round-trip to commit, and that consent must be affirmatively true. It also scopes the blast radius by stating signups/check-ins and private-domain audiences are untouched, which is exactly the reassurance a mutation tool needs.

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 dense clauses, no filler: precondition first, effect second, safe-commit protocol third, non-effects last. Every sentence carries load and the most decision-critical information (login, preview default, consent gate) is front-loaded.

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-param mutation with no output schema and minimal annotations, this covers purpose, preconditions, commit protocol, and side-effect exclusions. What it does not cover is what the preview response actually contains beyond 'before/after values' and whether re-previewing is needed after a partial toggle change – minor, but an agent assembling the call would benefit.

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 only 20% (just consent), so the description has to carry the rest and largely does: it explains preview's default-on behavior, the previewHash round-trip contract with matching parameters, and the meaning of true/false for the visibility toggles. It treats showPastActivities and showUpcomingActivities generically ('对应公开活动') and never distinguishes the two switches, leaving a small gap.

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?

Uses a specific verb+resource ('只改传入的本人开关' – only flips the caller's own passed-in toggles) and immediately defines the semantics of true/false for public homepage visibility. It also draws an explicit boundary against adjacent concerns ('不改变报名/签到或私域受众'), which lets an agent distinguish it from signup-audience tools in the sibling list 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 a clear two-phase operating procedure: preview by default, then re-issue with the same params plus previewHash, consent=true, preview=false only after explaining disclosure scope and obtaining explicit user consent. Login precondition is stated. It stops short of naming the read counterpart (get_my_activity_privacy) as the alternative, so it is descriptive of context rather than fully routing.

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