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

There are no annotations, so the description carries the full burden, and it does: it discloses the at-least-one-of constraint that the schema does not enforce, rate limiting, 60s edge caching, typical and p99 latency, and the feed_version cache-coherence field. It never contradicts anything because there is nothing to contradict.

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?

Sections are labeled and front-loaded, and the Returns block is genuinely necessary because there is no output schema. The one blemish is that the description opens with a bare constraint line before stating the tool's 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?

For a two-param lookup with no output schema and no annotations, it covers everything needed: purpose, alternatives, response shape including conditional fields, cost, and latency. 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 both params are already documented with examples, so the baseline is 3. The description adds real value by stating 'at least one of key_id or id is required', a constraint the schema does not express (required: []), which is the one piece of parameter semantics an agent could otherwise miss.

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 ('Single-item revocation lookup per Receipt Format v1.0 §8.2') and immediately scopes it against the bulk alternative, so it is distinguishable from get_receipt, receipt_lookup, and verify_receipt without opening a schema.

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?

Explicit 'Use this tool when' bullets name three concrete triggers (verify signature.key_id trust, verify receipt_id not retracted, recheck held receipts), and the 'Do NOT use' section routes the agent to fetching /.well-known/receipt-revocations.json directly and states that publishing is not exposed via this API.

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