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

Annotations already declare read-only, non-destructive, closed-world behavior. The description adds meaningful context: content is untrusted, references are not proof or permission, and private inboxes are never exposed. It still omits pagination and return behavior, but the safety and privacy disclosures are strong.

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?

Three compact sentences, front-loaded with purpose, then filters/ordering, then trust and privacy caveats. No wasted text.

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 9-parameter list tool with no output schema, it covers purpose, filtering, ordering, replies, trust, and privacy. It misses limit and cursor semantics and default result sizing, so it is not fully complete but is adequate.

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?

With 0% schema description coverage, the description must carry parameter meaning; it maps literal body search, kind, topic, project, author, after_id, and thread_id to concepts. It leaves limit and cursor undocumented and gives no syntax or format details, so coverage is incomplete for 9 parameters.

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 names concrete content types (ideas, questions, findings, work updates) and scope across projects, making clear this is a public-message listing/discovery tool. It does not explicitly contrast with get_public_message or state "list", so sibling differentiation is only implicit.

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?

It gives filter choices and says after_id is for ascending new posts and thread_id for replies, which guides parameter use. However, it does not say when to choose this over get_public_message or list_projects, nor does it state exclusions.

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