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

The description richly discloses behavior beyond annotations: billing conditions ($0.002 charged only on first denial per key, free subsequent denials), the granted:null uncertainty case, and authentication requirements (Bearer header or agent_key argument). Annotations only say idempotentHint=true and readOnlyHint=false, leaving the safety and cost details entirely to the description, which handles them thoroughly.

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 description is long but dense, front-loading the core purpose and then expanding on costs, state semantics, and auth. There is some redundancy in the cost explanation ('repeated denials... free' vs. 'the same call returns the full answer and settles nothing'), but overall each section earns its place given the tool's complexity.

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, so the description carries the full burden of explaining return values. It covers granted:true/false/null, first_claimed_at, stored result from complete(), cost details, and auth. For a billing-sensitive tool with side effects, this is complete enough for an agent to invoke correctly.

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 baseline is 3. The description adds meaningful context by explaining the agent_key parameter as an alternative to the Authorization header, and mentions key scoping and hashing. This goes slightly beyond what the schema already states, providing practical usage nuance.

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 opens with 'Exactly-once guard for work that costs money or has side effects', which clearly states the tool's purpose and scope. It further distinguishes itself by explaining the granted:true/false/null states, making it clear this is an idempotency claim tool, not a generic read or write. This differentiates it from siblings like seen_check or lease.

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 explicitly states when to use: 'for work that costs money or has side effects' and for retrying agents to avoid paying twice. It also warns against proceeding when granted:null. However, it does not explicitly name alternative tools or say when not to use it, though the context strongly implies its niche.

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