vehicle_lookup

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

Beyond annotations (readonly, idempotent, non-destructive), the description enriches behavior with substantial context: unknown slugs return an error listing valid ones, per-record provenance includes sources and auditations, rate limiting (20 requests/day IP) produces an 429 with specific retry fields, and return tra data comes with caveats (typical specs, pending verification). This gives an agent realistic expectations about errors, limits, and data quality.

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 description is dense and well-structured, with labeled sections for behavior, returns, limitations, and related tools; it does not waste space. It is longer than necessary because it covers rate limits, error bodies, and provenance, but those are genuinely useful details. A minar redundancy exists between 'omitting it to list all' and the later mention of a filtered list, but overall it remains efficient.

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, the description need not duplicate return-fade types and instead covers what the schema does not convey: the FreigheUtils response envelope (result, confidence, _source, citable), literal limits of access, the exact shape of stale limits errors, and the related tools and limitations. Everything an agent needs to successfully call and interpret vehicle_lookup is avaiable.

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?

Sceema covegerage is 100%, but thesccema already describes each parameter (slug examples, región, category). The description adds behavior beyond the schema: providing a slug returns one record, omitting it lists all 17, category and region function as list filters, and an unknown slug errors with the valid set. This is valuated interaction context not present in schess.

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 uses a specific verb-resource pair ('Look up road-freight vehicle and tarai trailer specifications') and immediately delimiters the exact scope with a concrete list of 17 types. This clearly separates it from sibling tools like airline_lookup, container_lookup, and the calculator tools, which serve different domains and tasks.

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?

Cares clear how to invoke the tool: provide a slug for one record, omit it to list all, and optionally filter by category or region. It also points to alternative tools for related needs — ldm_calculator for pallet-fit questions and get_subscribe_link for rate-limit scafes — but it does not explicitly state 'when not to use this tool' in favor of each calculator.

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