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

Annotations already declare read-only, non-destructive, closed-world, non-idempotent, and the description adds real behavioral context beyond them: no page fetch, no account access, no merchant contact, no money movement; the 0.10 USDC x402 charge with 10 signed-wallet free calls per 30 days; the X-Wever-Wallet-Proof binding to the exact JSON arguments and route; and an Ed25519 signed receipt. It also discloses the matching semantics and the deliberate limit that meaning is not interpreted. Minor gap: it does not say what happens on a failed or unpaid call.

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 purpose, input contract and cost/header requirements are front-loaded and almost every clause carries information an agent needs before calling. It is dense to the point of being a single wall of text, and the trailing contract path and human page URL are boilerplate a calling agent rarely uses, but nothing is fatally redundant.

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, yet the description still explains the return shape (a report categorizing each attribution plus an Ed25519 signed receipt) and the evaluation basis used to produce it. Combined with the stated read-isolation, pricing and wallet-proof requirements, an agent has everything needed to invoke this 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?

Schema coverage is 100%, so the baseline would be 3, but the description adds genuine semantics not in the schema: comparison is word by word, tolerating verbatim, elided and close variants, and it checks that the attributed person, role and organization appear with the passage. That tells the agent what the 'quote' and 'attributed_to' fields are actually measured against, which the schema does not.

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 names a specific operation on a specific resource: submit attributed quotes/endorsements plus source material and get a signed report marking each attribution as matching, differing or without a source. That is far more than a restatement of the name. It does not, however, explicitly distinguish itself from the many near-identical siblings (claim-, data-, terms-, translation-, benchmark-evidence-check), leaving the agent to infer the boundary from the resource noun alone.

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 implies the usage context ('submit attributed quotes or endorsements and the source material') and bounds it with 'Reads only the material in the call', so the agent knows the inputs must be supplied rather than fetched. It gives no when-not-to-use guidance and never names an alternative sibling for adjacent checks, which matters in a family of ~15 evidence-check tools.

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