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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing price ($0.01 USDC per call), the x402 payment flow, the failure mode (returns payment requirements without payment), and the exact retry mechanisms (X-PAYMENT or PAYMENT-SIGNATURE header, or params._meta["x402/payment"]). Note the 'POST' phrasing is transport-level and does not describe a mutation, so it is consistent with readOnlyHint=true rather than a contradiction, but an agent could briefly misread it as a write.

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 tight sentences: what it does first, what it returns second, cost and payment mechanics last. Every clause carries information (change categories, pointer/reason-code format, pricing, retry headers) and nothing is 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?

With no output schema, the description does the work of explaining the return payload (breaking vs non-breaking, JSON pointers, reason codes) and fully covers the unusual payment requirement. The one substantive hole is the unexplained 'mode' parameter, which an agent cannot infer from any structured field.

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?

The description reinforces the old/new parameters and adds genuinely new meaning by saying each may be a JSON Schema or an OpenAPI document, which the schema does not state. However, the third parameter, 'mode' (enum input/output), is undocumented in both the schema and the description, leaving a meaningful gap at 67% coverage.

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 ('POST two JSON Schemas or OpenAPI documents as old and new') and enumerates exactly what the result contains: breaking and non-breaking changes with JSON pointers and reason codes, covering removed properties, new required fields, narrowed types, enums and bounds, removed paths, operations, parameters and responses. That level of specificity separates it from loosely related siblings like catalog_diff or config_lint without needing to name them.

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 context of use is clear from the input framing (you must supply both an old and a new version), and the payment paragraph gives concrete invocation/retry procedure. There is no explicit when-not-to-use guidance or named alternative tool, so it stops short of a 5.

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