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

Beyond the annotations, the description discloses the privacy guarantee ("we never see it" — only the hash is transmitted), the output nature (signed, hash-chained attestation), the payment model and chains, and the transport/auth mechanism (POST JSON to paid_url with an x402 v2 PAYMENT-SIGNATURE header). These are exactly the preconditions an agent must satisfy before calling and are not derivable from readOnlyHint/destructiveHint/idempotentHint.

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 core purpose and privacy guarantee are front-loaded in the first sentence, with operational details (alternative tool, payment, endpoint) following in short clauses. A few lines are mildly redundant, such as "Paid tool — $0.25" immediately followed by "Paid URL: ...", but nothing is padded or off-topic.

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?

With an output schema present, the description need not explain the receipt contents, and it covers the pieces structured fields can't: privacy, pricing, chain, and the exact payment-header protocol. It omits anything about error behavior (e.g. malformed hash, rejected example keys, insufficient payment), which would have made it fully sufficient for a paid mutation tool.

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 100%, so document_hash's 64-hex pattern and the idempotency_key replay semantics are already fully documented in the schema. The description only restates that document_name is an optional label and adds no new constraint or format detail beyond the structured fields; 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?

"Prove a document existed: send its SHA256 hash ... for a signed, hash-chained attestation" gives a concrete verb (prove/attest) and resource (document by hash), and the privacy clause clarifies exactly what is submitted. It differentiates against check_url_custom for live URLs, but never mentions the closest sibling attest_work, so the boundary with the other attestation tool is left implicit.

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?

It explicitly routes a related case elsewhere ("Live URLs: check_url_custom") and states the payment precondition ($0.25 USDC on Base or Arbitrum One) plus the required x402 header, which are real gating conditions. It stops short of a full when-to-use vs when-not framing, e.g. it never says when attest_work is the better choice.

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