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

Annotations only declare readOnlyHint=true, so this text carries real weight: contacts are masked by default, includeContacts requires explicit user authorization, ID documents cannot be freely decrypted, and answers are withheld unless `fields` names them. It also discloses return-shape behavior not captured by the schema (pendingActivations capped at 200, overview limited to the first screen), though those references are cryptic because no such parameters exist in the schema.

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?

Every clause carries information, and there is little padding, but the semicolon-chained shorthand is not front-loaded: the tool's purpose never appears as a leading sentence, and terms like 'overview' and 'pendingActivations' appear without context. It reads as terse operator notes rather than a structured definition.

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 an 11-parameter tool with no output schema, the description does cover the critical unknowns: access requirement, contact masking, answer withholding, and where to go for exports or bulk actions. However, `since`, `until`, `cursor` and `channel` get no treatment at all, and pagination behavior across cursors is left entirely to the schema.

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 schema already explains q, limit, status, reviewStatus, fields and includeContacts, and most description clauses restate them ('limit默认20≤50', 'status投递态、reviewStatus录取态'). The only genuine additions are the masking/authorization policy and the 'default key/nickname, use fields for answers' default behavior, which is a modest delta over a fully documented schema.

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 title and name imply 'list signup submissions for one activity', and the description names its resource indirectly through 'q搜账号/答案', 'status投递态、reviewStatus录取态' and '整表另用导出'. However, it never states a plain verb+resource sentence such as 'list signups for a slug', so an agent must reconstruct the purpose from parameter commentary rather than read it.

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?

'整表另用导出' explicitly routes full-table needs to the export tool, and '批量处置先预演确认' points at the bulk-review sibling with a required preview step. The '登录/主办方' prefix also states the access prerequisite, though no explicit 'do not use this when…' exclusion is given beyond the export redirect.

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