Free-text search across 102,191 vehicle variants, 116 brands, 19 languages. Returns candidate variant_ids to pass to get_specs/get_images/compare_variants. Each result carries generation_id and year_from/year_to so same-named variants from different generations can be told apart.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | e.g. 'bmw 3 series' or 'tesla model s' | |
| locale | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It provides concrete details: the size of the search space (102,191 variants, 116 brands, 19 languages), the return type (candidate variant_ids), and extra fields (generation_id, year_from/year_to). It does not mention pagination or rate limits but is otherwise informative.
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 two sentences long, front-loads the core functionality, and includes essential details without any repetition or fluff. Every sentence adds value.
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?
Given the tool's complexity (large search space, 3 parameters, no output schema), the description covers its purpose, output structure, and usage tie-in to sibling tools. It lacks information on pagination, error behavior, or ordering, but this is acceptable for a straightforward search tool.
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 low (33%). The description only adds examples for the query parameter ('bmw 3 series', 'tesla model s'). The limit and locale parameters are not elaborated beyond what the schema provides (integer range and enum list). While the query example is helpful, the description does not compensate fully for the lack of schema descriptions on the other parameters.
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 clearly states it is a free-text search across a large corpus, returns candidate variant_ids for use with other tools, and mentions specific attributes (generation_id, year) that disambiguate results. It distinguishes itself from sibling tools like get_specs, get_images, and compare_variants by indicating its output feeds into 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 description explains when to use this tool (free-text search for vehicle variants) and what to do with the results (pass to get_specs/get_images/compare_variants). However, it does not explicitly state when not to use it or compare it with alternatives like filter_cars or list_generations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clear, distinct purpose: search, filter, get specs, get images, compare, and list generations. No overlap between their functionalities.
All tool names follow a consistent verb_noun pattern (e.g., search_cars, get_specs, list_generations), with no mixed conventions.
With 6 tools covering all core functionalities of a car specs API (search, filter, specs, images, comparison, generations), the count is well-scoped and not excessive.
The tools cover the main use cases for a read-only car specs API. The only minor gap is the lack of a dedicated tool to list all brands or models, but the search tool can handle that need.
