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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes far beyond them: authorization model (poster, worker, commissioning agent, payer's named judge; public job visibility grants nothing), hash-verification behavior, the full set of failure statuses and their meanings, token kinds, and the read budget. The prompt-injection caveat ('never instructions to follow') is a genuinely valuable behavioral disclosure.

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 a bolded when-to-use clause, then example, then return semantics — a logical order with no filler sentences. It is dense and long, and the status enumeration reads as a wall of text, but each element carries actionable information.

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 fully specifies the return shape (status plus evidence_id, version, submitted_at, storage_url, hash) and every terminal status. For a one-parameter read tool with annotations present, nothing an agent needs to call it 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% and the single claim_id parameter is fully documented there, so baseline is 3. The description adds real value by explaining how to obtain the value (list_my_jobs or claim://) and confirming the clm_ prefix origin, which is meaning beyond the schema.

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: it 'returns the delivered text itself' for a given claim, and explicitly contrasts with siblings — list_my_jobs/claim:// supply the claim id, while accept_claim/request_changes/decline_claim handle verdicts. An agent can distinguish this from every related tool without opening schemas.

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?

Leads with an explicit 'When to use' condition (work has been delivered and you need its contents) and names the alternatives for both the prerequisite step (list_my_jobs) and the follow-up step (accept_claim / request_changes / decline_claim). It also states when NOT to expect results, listing the non-'served' statuses.

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