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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description still earns credit by disclosing the auth prerequisites (sign-in plus a verified referrer account) and the external side effect — the candidate is notified to watch their email, which reaches the company. It does not say whether the mark can be undone or what happens if it is called before submission truly occurred.

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?

Four compact sentences, no filler, and the prerequisite is front-loaded before the effect. The first sentence's comma placement ('sign-in, and a verified referrer account') and the fragmentary style of the last sentence are slightly rough, but 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?

With a single required parameter, an output schema, and full annotation coverage, the description supplies exactly the pieces the structured data cannot: auth requirements, the claim-before-submit precondition, and the candidate-facing notification consequence. Only the irreversibility/error path is left unstated, which is a minor remaining gap for a destructive tool.

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?

The schema documents request_id at 100% coverage and already points to list_referrer_requests as the source. The description adds a constraint on which request_id is valid ('only for a request this referrer claimed'), which is real meaning beyond the schema, but it adds nothing about type, format, or failure behavior for the parameter.

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 and resource ('marks a claimed request as referred') and then defines what 'referred' actually means — the referral was submitted in the company's own system. That semantic definition is more than the title gives. It stops short of naming the sibling it supersedes (claim_referral_request), but the phrase 'a request this referrer claimed' implicitly scopes it away from the claim tool.

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 concrete preconditions: sign-in required, verified referrer account required, the request must have been claimed by this referrer, and the submission must have actually happened. That is a clear when-to-use test rather than an implied one. It does not name an alternative for the negative case (e.g., decline_referral_request or report_referral_request when no submission occurred), which is the main gap.

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