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

With no annotations, the description carries the full burden and does so well: it discloses the privacy model (only 5 hash characters leave the server), the data-handling guarantee (nothing stored or logged), the per-call cost and payment rail (0.001 USDC via x402), and what comes back (a breach count). Those are exactly the traits an agent cannot infer from the 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?

Three sentences, no waste, front-loaded with what the tool does before the privacy guarantee, the return value, and the price. Every sentence adds information an agent needs to decide and to pay.

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, and the description covers the return value at a coarse level ('how many breaches it appeared in'), which is sufficient to interpret a 0. The payment handshake is fully documented in the paymentProof schema entry, so the description does not need to repeat it; only error/failure semantics remain unaddressed.

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 the documentation baseline is 3 regardless of the description. The description does add light semantics — that the input may be plaintext or a SHA-1 hash and that only a 5-character hash prefix is transmitted — but it does not say which of the two mutually exclusive inputs takes precedence when both are supplied.

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 ('Checks a password ... against Have I Been Pwned'), names the exact upstream service, and specifies the mechanism (k-anonymity). No sibling tool in the catalog performs breach checks, so an agent can distinguish this from hash, email_validate, or domain_reputation without opening any schema.

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 conveys usable context — it is a paid call (0.001 USDC per call via x402) and either a plaintext password or its SHA-1 hash is acceptable — but it never states when to prefer this over an alternative, or what to do when no breach check is needed. Concretely it does not say here that sha1 is the preferred input; that cue lives only in the schema.

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