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

Annotations cover the safety profile (write, non-idempotent, non-destructive, open-world), and the description adds real behavior beyond that: publishing is immediately live and public, a stale draft produces 409 compose_version_stale with the recovery procedure, 422 returns `missing`, and publishing may be blocked by organizer-qualification requirements that the agent cannot satisfy (needs a verification code in the App). No contradiction 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 and clearly partitioned by bracketed labels (audience/scope, chain, pitfalls), with the public-visibility consequence stated first. It is dense and slightly run-on in the pitfalls section, but nearly every clause carries actionable information.

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 2-param mutation with no output schema, it covers trigger, prerequisite chain, optimistic-lock recovery, validation errors and qualification gating. The main remaining gap is what the call returns (activity id / link / resulting status) so the agent knows how to follow up beyond the letter branch.

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 the baseline is 3, but the description adds procedural meaning: `version` must be the value just read from get_activity_draft, and reusing an old version after an external edit triggers 409. composeId gains nothing beyond the schema's pointer to import_activity_draft / list_activity_drafts returns.

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 ('publish draft → create activity') and enumerates exactly what becomes public (title, time, location, byline, intro, signup form), including the moderation stance (先过后审，立即上线). This clearly separates it from update_activity_draft, get_activity_draft and import_activity_draft 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 trigger ('user says 发布'), a named prerequisite (get_activity_draft must return empty `missing`), an explicit ordering chain (read draft → publish with that version → render_activity_letter if a letter is wanted), and named exclusions/failure branches (409 stale, 422 missing, insufficient organizer qualification).

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