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

Annotations only declare readOnlyHint and openWorldHint; the description adds material context beyond them: complaints are 'unverified owner reports' (data-quality caveat), the total count is NHTSA's while 'the returned list is a slice' (pagination/completeness caveat), and the x402 payment model with failed calls uncharged. These are exactly the operational traits annotations cannot express.

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?

It is front-loaded: the resource and returned fields come first, then caveats, then sibling routing, then price. The final pricing sentence is long but discloses cost the agent needs, so it earns its place; otherwise the text is dense but readable.

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, return-shape explanation is not required, and the description covers scope, data-quality caveats, slice semantics, alternatives and cost. Nothing an agent needs to select or call this tool is missing.

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 make, model, year and limit are already documented in the schema, making 3 the baseline. The description only restates the make/model/year key and hints at slicing behavior for limit without adding format or range detail.

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 description opens with a specific resource and scope: 'US NHTSA owner-filed vehicle complaints for a make, model and model year', then enumerates the returned fields (incident date, components, summary, crash/fire flags, injury counts). It explicitly names the two sibling tools it is not (recalls, VIN decoder), so an agent can route without opening a 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?

It names both alternatives with the condition that selects each: travel_nhtsa_vehicle_recalls 'when you need US NHTSA safety recalls for a make, model and model year', and travel_nhtsa_vpic_vehicle_decoder 'when you need to decode a VIN'. That is explicit alternative routing rather than implied usage.

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