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

While annotations already declare readOnlyHint, idempotentHint, and destructiveHint, the description adds meaningful behavioral context: it performs verification without log lookups (i.e., no server-side state), equivalent to an offline script, and does not perform on-chain anchor checks (pointing to another endpoint). This transparency about what the tool does and does not do goes beyond the annotations.

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 two sentences of substantive content plus a third sentence pointing to an alternative. It front-loads the purpose, lists specific checks, and includes a clear pointer to related functionality. No filler or redundancy—every sentence earns its place.

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 tool is cryptographically complex, but the description covers its core behavior, the exact checks, the lack of trust assumptions, and references an offline script for reproducibility. An output schema exists, so return value details are not needed. The pointer to the alternative endpoint fills the only gap (on-chain consistency). This is fully complete for an agent to decide and 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?

The schema describes the single parameter 'receipt' with its expected format (bare or wrapped in {receipt}) and sources. The description adds the version specifier 'gblin-receipt/v1' and clarifies it's JSON, but these are minor additions. Since schema coverage is 100%, the description provides modest extra value, warranting a 4 rather than the baseline 3.

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 starts with the specific verb 'Verify' and identifies the exact resource: 'a gblin-receipt/v1 JSON'. It enumerates the specific checks performed (leaf hash, Ed25519 signature, RFC 6962 inclusion proof, etc.), which clearly distinguishes it from sibling tools like receipts.seal or receipts.get. The phrase 'pure math (no log lookup, no trust in this server)' differentiates it further from trust-based checks.

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 this tool: to verify a receipt with pure math and no trust in the server. It also provides an alternative for a different need: 'For the extra on-chain-anchor consistency check use GET /v1/verify/:index.' This gives clear context and exclusions, making the usage boundaries obvious.

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