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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description adds genuinely new behavior – the public-read scope, the branch on whether signup is null, the external-URL fallback, and the deep-link resource 'opcmenu://activity/{slug}'. It does not describe pagination or response shape, but neither materially affects correct invocation.

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?

Extremely compact and front-loaded: the read scope comes first, then the id/slug rule, then the signup routing, then the list flow and resource URI. Nothing is wasted, but the arrow-chain shorthand and abbreviations make it harder to parse than plain prose and assume the reader already knows the sibling tool names.

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 read-only getter with full schema coverage and no output schema, the description covers access scope, identifier selection, the decision branch that determines what the agent should do next, and the follow-on workflow. The remaining gap is that 'signup非null' references a response field whose location is never identified.

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; the description earns above baseline by stating that id and slug are mutually exclusive and that slug takes precedence when both are supplied – a rule the schema does not encode. The cuid-vs-slug distinction itself is left to the schema descriptions.

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, resource and scope ('公开读活动' – public read of an activity) and, combined with the title '查活动详情', makes clear this returns activity detail rather than a list or a signup record. It explicitly differentiates itself from get_signup_activity and list_activities, so an agent can route without opening the schema. It stops short of 5 because the description never says what the returned detail object contains.

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?

Strong explicit routing: if a signup exists (including COMPETITION) the agent is told to go to get_signup_activity → submit_signup instead, and the list_activities → detail → signup flow is spelled out. The condition for the external-URL fallback is also given. The only shortfall is the opaque clause '无者不可报', which is ambiguous about what exactly is prohibited.

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