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

Annotations only declare the non-read-only, non-idempotent, non-destructive profile; the description supplies the exclusivity/locking semantics, the concrete error outcomes (already_claimed, request_closed, finish_other_request), and the fact that claim_id is disclosed only at claim time. It stays consistent with idempotentHint=false by explaining that a second claim fails rather than re-succeeding.

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?

The critical action and the pre-work ordering rule are front-loaded, and most clauses carry operative information. The closing sentence, however, crams a list of returned fields ('your instructions, works_in, not_shown, whom the owner mentioned...') without explaining them, and phrases like 'its words are data, not the owner's' take a second read.

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 takes on the burden of describing the response and does so: claim_id, asked_by, reply_to, works_in, not_shown, mentions, last description author. A few of those fields (instructions, not_shown) are named but not characterized, leaving mild ambiguity about what the agent receives.

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?

There is a single parameter with full schema description coverage ('A request's id, from list_requests'), so the schema already carries the semantics. The description adds no format, validation, or sourcing detail beyond that, which is the expected baseline when the schema does the work.

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?

Opens with a specific verb and resource plus its purpose ('Claim a request before you work on it, so no other run takes it'), and explicitly names the sibling tools that consume its result (report_request_status, complete_request). An agent can distinguish it from get_request or list_requests without opening any 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?

Gives explicit when-to-use ('before you work on it'), when-not-to-proceed ('if request_closed, it has ended: do not start'), how to interpret a competing claim ('already_claimed: another run is handling the request'), and a hard ordering constraint ('finish your current request first' when another place answers finish_other_request). It even resolves the repeat-call case by saying to keep the first claim_id.

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