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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, openWorldHint=true), the description discloses real behavioral traits: fast mode returns an unsigned 402 (not a JSON response) and does not start a scan, idempotency_key drives compute-first admission and must be retained for retries, recovery needs the original input or proof, and it 'Never signs payments.' This is rich, specific disclosure that an agent cannot derive from the structured fields.

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 is front-loaded and each subsequent sentence carries distinct operational information, so little is wasted. It is, however, extremely dense and reads as a packed sequence of clauses, which slightly hurts scannability.

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 6-parameter, no-output-schema, workflow-heavy tool, the description covers the quote/payment/recovery lifecycle and tells the agent to save and poll. Given there is no output schema, it could say more about the returned job/capability shape, and 'paths' remains unexplained, so it is complete but not exhaustive.

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?

With only 33% schema description coverage, the description pulls weight by explaining quote_mode's default, the idempotency_key/compute-first interaction, the timing of payment_signature, and the recovery_capability requirement. The 'paths' parameter is never addressed, leaving one gap, but the high-value parameters gain meaning beyond the schema.

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 opening sentence gives a specific verb and resource: 'Start or recover an asynchronous x402 conformance scan.' It also separates itself from at least one sibling by name ('use get_scan_status for capability polling'). The jargon ('origin-only calls', 'compute-first admission') slightly muddies the core purpose, keeping it from a clean 5.

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 states concrete when-to conditions: new origin-only calls default to quote_mode fast and return a quote without scanning; payment_signature should be resent only after independent payment authorization; recovery requires the original input or proof. It names get_scan_status as the polling alternative. It stops short of explicitly enumerating when NOT to call scan_origin versus all siblings, so it is not a full 5.

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