Filter values

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description's job is to add context — and it does: region returns states only unless query is supplied, and 'not every kind exists for every section' warns of empty/varying results. It stops short of describing the actual response shape (list of plain strings vs. label/value pairs), which is the main remaining behavioral gap.

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?

Purpose is front-loaded in sentence one, then usage rules and per-section routing follow in descending priority. Dense but purposeful; a few fragments (the region/query syntax note) could be tightened, and the parenthetical enumeration is slightly redundant with the enum.

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 three-parameter lookup tool with no output schema and full annotation coverage, the description supplies the decision rules an agent needs: when to call it, how query scopes region, and section-specific kind selection. The absence of any description of the returned structure (only one inline value example) is the notable omission.

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 coverage is 67% and the schema already documents query and vehicle_type, but the description adds real meaning: which kind values pair with which vehicle_type, that query only applies to region and usage, and the truncation behavior of an unfiltered region list. It does not explain all enum members (drive, cylinder, economy, lifestyle, origin, body_status), so not every kind is disambiguated.

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?

Opens with a specific verb and resource ('List the allowed values of one ba_search filter') and enumerates concrete example domains (states/cities, body types, fuels, colors, years). It explicitly positions itself as a lookup helper for the sibling tool ba_search, so an agent can distinguish it from ba_search without inspecting schemas.

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?

Gives an explicit when-to-use rule ('Use it before ba_search when you need an exact value') with a worked example (kind=region query=اصفهان → 'isfahan'), plus a when-not case ('transmission needs no lookup: manual or automatic'). It further routes by section, telling the agent to use vehicle_type=truck with kind=usage and vehicle_type=motorcycle with body/fuel/color.

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