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

With no annotations, the description carries the full burden and does well: 'Never pays. Free.' directly answers the main risk (an agent triggering a payment) and implies a read-only probe of the unpaid 402. It also discloses exactly what is inspected per directory, which is real behavioral content beyond the schema. It stops short of stating whether network calls are made to third-party directories, any rate limits, or how partial/indeterminate results are reported.

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 verb and resource, and the two short trailing sentences ('Never pays. Free.') are high-value. The middle sentence is a single very long parenthetical enumeration of four directories' criteria, which is dense but every clause carries information an agent cannot get elsewhere. Slightly heavy on structure, but no filler.

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 two-parameter read-only lint tool with no output schema, the description covers what is checked, against which authorities, and why it is safe to call. The main omission is a hint about the shape of the report (per-directory pass/fail plus reasons), which matters since there is no output schema to describe it. Otherwise complete.

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% and both parameters (url, method with an auto/GET/POST enum) are documented in the schema, including the 'auto: tries both' behavior. The description adds no further meaning about the parameters — it never clarifies that the URL must be the paid endpoint or how method interacts with the unpaid-402 check. 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 — lints an x402 endpoint's unpaid 402 response and reports, per directory, whether it meets that directory's listing requirements, naming the four directories (x402dash, x402scan, the402, CDP/PayAI Bazaar) and their individual criteria. The purpose is unmistakable. It does not, however, differentiate itself from the sibling tools lint_payment_required and lint_x402_endpoint, so an agent must infer the boundary.

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 implied: you run this to see whether an endpoint would be accepted by the major x402 directories before attempting listing. There is no explicit when-to-use/when-not-to-use statement and no routing to the two sibling lint tools, so the agent has to infer which of the three to call. The closing note 'listing then needs one settled payment' gives useful follow-on context but not selection guidance.

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