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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries the behavioral burden. It adds significant context beyond annotations: the claim_won:true contract, the rule that an unchanged result means non-winner and 'must not start work', cost ('Free'), and auth requirement ('requires the 'act' scope'). This is exactly the operational detail an agent needs for a conditional claim operation.

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 short sentences, each earning its place: purpose, invocation, winning condition, losing condition, plus scope/cost. Critical safety constraints are front-loaded immediately after the purpose statement. No filler or repetition of schema content.

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 correctly explains the essential response contract (claim_won:true, unchanged means non-winner). It covers the nuanced nullable attempt_id and the destructive safety boundary. The only minor gap is not describing error/failure responses for invalid job_id or expired attempts, which an agent could encounter.

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%, so the schema already documents all three parameters, including that job_id is from list_queue and attempt_id is exact and nullable only for legacy jobs. The description adds marginal value by restating provenance and emphasizing exactness, but does not meaningfully exceed schema content, so baseline 3 is appropriate.

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 opening phrase 'Try to claim one queued preparation attempt' names a specific verb (claim), resource (queued preparation attempt), and conditional nature. This clearly distinguishes it from siblings like list_queue (listing), get_claims (reading claims), and record_claim (recording outcomes) without ambiguity.

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?

The description gives clear invocation context: 'Pass job_id and the exact nullable attempt_id from list_queue' establishes the prerequisite workflow (list_queue feeds this tool). It does not explicitly name alternatives or state when-not-to-use, so it falls short of a 5, but the usage context is unambiguous.

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