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

Annotations only flag non-readOnly / openWorld / non-idempotent / non-destructive; the description adds the login requirement, the preview-by-default safety behavior, the mandatory consent gate, the previewHash confirmation handshake, and what side effects are explicitly excluded. That is substantial context the structured fields do not carry, and it is fully consistent with the annotations.

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 the login precondition, then behavior, then the execution protocol, then the exclusion clause — a sensible order for an agent scanning it. It is compressed into a few long semicolon-linked clauses, so the consent/previewHash flow takes a second read, but there is no filler.

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 mutation with no output schema and no required fields, the description covers auth, the confirmation workflow, and non-effects. Return expectations are only implied by 默认预览前后值 (preview returns before/after values plus a hash), so the response shape is left partly to inference, but nothing critical for correct invocation 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 description coverage is only 20% (consent alone), so the description must carry the load and largely does: it explains preview's default-on behavior, that preview=false is the execute path, where previewHash comes from, and the true/false meaning of the visibility switches. It leaves the exact past-vs-upcoming switch mapping and previewHash lifetime implicit, which keeps it short of a 5.

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+resource: it changes only the passed-in personal (本人) homepage activity-visibility switches, and it defines what true/false mean for the public homepage audience. It also fences itself off from adjacent tools by noting it does not touch 报名/签到 or 私域受众, separating it from update_my_profile-style tools.

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 two-step protocol: call with defaults to preview before/after values, then re-issue with the same parameters plus previewHash, consent=true and preview=false after explaining disclosure scope and obtaining consent. Login requirement is also stated up front. It never names the read-side alternative (get_my_activity_privacy), so the routing side is slightly incomplete.

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