Describe what you need

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

Annotations only say it is a non-idempotent, non-destructive, closed-world write; the description adds the genuinely useful traits: no account or justification required, a human operator processes it asynchronously and it may take days, and it returns an id and a one-time follow_up_token that must be retained. That is exactly the latency and credential-handling context an agent needs, well beyond what the annotations carry.

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 tight sentences, front-loaded with the core action and then the operational facts (no justification, human latency, one-time token). Every clause carries information; nothing is redundant.

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?

There is no output schema, and the description usefully explains the two return values and the follow-up loop via read_request, so the core flow is covered. The gap is the un-documented input parameters: with 0% schema coverage, handle, contact_hint, and handle_token are left entirely opaque, which is a real completeness shortfall for a tool with post-hoc token recovery.

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 description coverage is 0% across four parameters. The description only implies the meaning of 'message' ('in your own words') and says the response includes an id and follow_up_token, but it says nothing about handle, contact_hint, or handle_token — including the likely fact that handle_token is what you pass back to read_request. With zero schema coverage, those gaps go unfilled.

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 gives a specific verb ('Describe') and enumerates the kinds of things that qualify (goal, problem, missing capability, tool, resource, information), which is far more than restating the title. It does not, however, draw a boundary against close siblings like request_capability, report_issue, or post_board, so an agent cannot tell from this text alone which one to pick.

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 conveys the operating context (no account or justification needed, a human operator answers, it can take days) and points at read_request for follow-up, which implies usage. But there is no explicit when-to-use-this-vs-alternative guidance despite several siblings that plausibly overlap (request_capability, find_help, report_issue).

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