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

Annotations only declare it as a safe read; the description goes much further, disclosing result ordering, the exclusion of requester identity, that reply appears only on explored/declined rows, that trivia-targets carry a closed/spoiler mark, and that nextOffset=null terminates paging. That is substantial behavior beyond the structured fields.

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?

Dense but front-loaded — what the tool returns comes first, exclusions second, then filters and paging. The sentences are long run-ons and a limit/offset clause is missing, but there is no filler wording.

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?

With no output schema, the description does the work of explaining return shape: reply semantics, target composition, nextOffset termination and exclusion of submitter identity. It stops short of enumerating all returned fields, but it is sufficient for a five-parameter filtered list tool.

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 0%, so the description carries the burden and largely does: status values are glossed with their meanings, gameSlug is described as covering the work plus its 工夫・噂・トリビア requests, and query is defined as a partial match on the body. limit and offset are only implied by the paging sentence, leaving a small gap.

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 and resource — reader-submitted investigation requests, newest first — and explicitly equates them with the «みんなの依頼» screen. It also draws a hard boundary by excluding 要望・指摘・情報提供, which separates it from the claims-style sibling tools without the agent needing to open a 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?

Usage context is clear: open/in_review/explored/declined statuses, filtering by status, gameSlug and query, and paging via nextOffset. The exclusion sentence tells the agent which class of data belongs elsewhere, but no sibling tool is named explicitly, so the routing is implied rather than stated.

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