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

With no annotations, the description carries the full burden and largely meets it: it discloses price and payment rail (x402, eip155:8453, $0.004/call), the EOA EIP-712-only constraint with ERC-1271/6492 unsupported, the 64 KiB MCP body cap, and the crucial caveat that source origin and field-value support are not authenticated. The remaining gap is that it never describes the response shape (e.g. per-field findings vs. a flat list of issues), which matters more here because there is no output schema.

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 opening sentence front-loads the operation and its finding categories, and the payment/limit clauses are terse. There is some redundancy — 'input facts are not authenticated' restates the earlier 'neither source origin nor support for a field value is authenticated' — and the bracketed price banner crowds the front, but nothing is padded.

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 tool with no annotations, no output schema and three 0%-documented parameters, the definition should state what comes back and what as_of does. It covers cost, payment constraints and the authentication caveat well, but the caller still cannot predict the result structure or the meaning of the one non-required input, leaving a real completeness gap.

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 description coverage is 0%, so the description must compensate, and it does so only indirectly: 'up to 1000 supplied product fields' maps to fields, 'declared expiry' to valid_until, 'future or undated observations' to observed_at, and 'content identity hashes' to content_sha256. The required as_of parameter and the semantics of source_ids/reference are never explained, so half the input surface remains guesswork.

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 gives a specific verb and resource ('Inspect up to 1000 supplied product fields and sources') and enumerates exactly the four classes of findings produced: missing references, declared expiry, future/undated observations, and content identity hashes. That is far more precise than a tautology, but it never contrasts itself with the closest sibling, data_freshness_check, which an agent could easily confuse it with.

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?

Usage is only implied: you call it when you already hold a set of fields and their source records and want provenance hygiene checked. The only explicit exclusions are behavioral ('References are never fetched') rather than situational, and there is no statement of when to prefer data_freshness_check or verify_attestation instead.

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