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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds real value: login requirement 【需要登录】, that no full source text is returned, and the caution that 'rejected' means missing evidence so the agent must not fabricate. These are behavioral traits beyond 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?

Very dense but front-loaded: login prerequisite first, then payload contents, then workflow routing, then the rejected caveat. Every clause carries information; the only cost is heavy jargon that assumes domain fluency.

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 exists, so the description must carry the return-value burden and does so thoroughly (what fields come back, what is excluded). Combined with the annotations and single fully-specified parameter, an agent has what it needs to call it correctly.

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% and the single composeId parameter is fully documented in the schema. The description adds no additional parameter meaning, so baseline 3 applies.

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: reads an activity draft summary, then enumerates what it returns (intro ≤300 chars, missing/questions/nextQuestion, image review status, importState) and explicitly notes it excludes the full source text. This distinguishes it from update_activity_draft and publish_activity_draft, though those are framed as next steps rather than contrasts.

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 explicit workflow routing: '只问nextQuestion，再update_activity_draft' and 'missing空时publish_activity_draft带当前version'. The agent knows when to move on to update vs publish. Falls short of a 5 only because the 'when not to use' side (vs other draft read tools) isn't stated.

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