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

Goes well beyond the readOnly/idempotent annotations: it discloses the trust anchor (merchant key fingerprint at key_anchor), the temporal scope of the proof (snapshot.generated_at, not current price/stock), the exact returned artifacts, and a pointer to an independent verifier. This is exactly the kind of caveat an agent needs to avoid misusing the result.

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?

Front-loaded with the core purpose, then the trust anchor and the snapshot-timestamp caveat, all in a compact block. Dense but every clause carries signal; only the enumerated payload list could be trimmed marginally.

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 must describe the return, and it does: signed row, bucket hashes, Ed25519-signed manifest, merchant public key, and step-by-step verification, plus an external verifier URL. Combined with the trust-model and timestamp caveats, an agent has everything needed to call and interpret it.

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?

With 1 parameter at 100% schema coverage, the schema already documents p2209_id including its source (global_search) and example. The description adds only that the id identifies 'this offer's product row' and does not extend the parameter meaning further, so baseline 3 applies.

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: 'Returns a cryptographic proof that this offer's product row is exactly the one the merchant signed in its catalog snapshot,' and enumerates the payload contents. This distinguishes it from siblings like verify_offer and get_product, which serve different verification/retrieval purposes.

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?

Clarifies the trust model ('anchored on the merchant domain, not on KaliCart') and scopes the guarantee ('proves the row as signed at snapshot.generated_at, not the current price or stock: the checkout is authoritative'), which tells an agent when this proof is and isn't the right evidence. It does not explicitly name alternatives such as verify_offer for live data, so it stops short of full routing guidance.

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