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

No annotations are provided, so the description fully carries the burden of behavioral disclosure. It goes well beyond a basic read operation: it states the endpoint is an alternative to a local mirror, includes `feed_version` for cache coherence, details response fields (`revoked`, `revoked_at`, `reason`, etc.), and discloses cost, rate-limiting, edge-caching (60s), and latency ranges. This level of detail is exceptional and leaves little ambiguity about side effects or operational behavior.

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 organized into clear, labeled sections (purpose, use cases, non-use cases, inputs, returns, cost, latency) with bullet points for scannability. Every sentence adds operational value—the cost and latency sections are not fluff but pragmatic details for an agent deciding whether to use this endpoint. It is longer than average but tightly written and front-loaded with the core purpose.

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?

The description is fully self-contained for a tool with no output schema and no annotations: it explains the input options, the exact response structure, the cache/rate-limit behavior, and even provides fallback guidance (fetch well-known directly). There is no missing context an agent would need to make an informed invocation decision. The only minor omission is explicit authentication requirements, but the 'Free; rate-limited like the rest of the data API' implies public access, and the overall completeness is outstanding.

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% with both parameters already having descriptions and examples. The description adds the critical constraint 'Provide one of `key_id` or `id`', which is not encoded in the schema, and reinforces the context for each parameter (e.g., 'Receipt-format key_id'). This adds meaningful semantics beyond the schema, though the schema already does most of the heavy lifting.

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 'Single-item revocation lookup per Receipt Format v1.0 §8.2', immediately stating the specific verb ('lookup'), resource ('revocation'), and scope ('single-item'). It further distinguishes this tool from siblings like 'get_receipt' and 'verify_receipt' by contrasting it with fetching the full revocation set. This is a clear, specific purpose statement that differentiates the tool effectively.

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 provides explicit 'Use this tool when' and 'Do NOT use this tool when' sections, enumerating concrete scenarios (verifying a receipt's key_id, checking a specific receipt_id, long-term rechecking) and explicitly naming the alternative (fetching `/.well-known/receipt-revocations.json` directly) for the negative case. This gives an agent unambiguous guidance on when to invoke this tool versus another resource.

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