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

Annotations only declare readOnlyHint/openWorldHint; the description adds substantial behavior beyond that: hard caps of 40 messages and 20,000 characters per call, `hasMore`/`nextCursor` resume semantics with no gap or duplicate, and the fact that `messageCount` stays the thread total rather than the page count. It also discloses privacy behavior (`messagesHidden` for private documents), permanence ('nothing is ever destroyed'), and `orphaned:true` for deleted blocks/tasks — exactly the non-obvious traits an agent needs.

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 with purpose and the answering-question framing, then filters, then pagination/privacy edge cases — a defensible order. It is a dense single block that duplicates some schema-stated filter semantics and leans on ALL-CAPS emphasis, costing a point on efficiency.

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 10 optional params and no output schema, the description carries the return-shape burden and does: `messages` with author/dates oldest-to-newest, `messageCount`, `hasMore`, `nextCursor`, `messagesHidden`, `orphaned`. Nothing material an agent needs to call this correctly is missing.

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 documents each parameter; the description adds cross-parameter meaning the schema states less clearly — e.g. that `since` interacts with `includeMessages` to return only later messages, that `threadId` bypasses the `status` filter, and that naming a hidden thread's `threadId` changes nothing. It does partially restate the filter list, keeping it below a 5.

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 ('Lists the comment threads of the project') and immediately frames the user question it answers ('which comments were left on X?'). The scope is unambiguous versus the write-side siblings (add_comment, reply_comment, resolve_comment) because it is explicitly a listing/reading operation.

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 clear when-to-use guidance: without `includeMessages` you only get counters, with it you read the discussion, and `since` + `includeMessages` is for polling an ongoing thread. It also ties itself to get_document's `comments` field. It does not explicitly exclude or route away from any sibling (e.g. 'do not use to post, use add_comment'), so it stops short of a 5.

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