Search filters

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the bar is lower. The description still adds real behavioral context the annotations cannot: a query or category is required in practice (both schema params are optional), and brand coverage is only exhaustive once a category is known — an important completeness caveat for the agent's downstream filtering.

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?

Two short blocks, zero filler: the return surface is front-loaded, then the usage rule and the completeness caveat. Nothing is repeated from the schema and no sentence is decorative.

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 no output schema, the description does the work of describing the return shape (the list of filter dimensions), and it warns about incomplete brand data without a category. The one residual ambiguity is what happens if neither optional parameter is supplied, which is left unspecified.

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 100%, so a 3 is the baseline. The description earns above baseline by stating the at-least-one-of relationship between the two optional parameters — an invariant the schema does not enforce — and by tying `query`/`category` to concrete downstream uses (category id, brand id, attribute slugs).

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 first sentence names the resource (search filters) and enumerates exactly what it returns: category children, brands, price span, sort options, attributes. That is specific enough to separate it from tb_search, though it does not acknowledge the overlap with siblings like tb_category and tb_brands, which also surface some of this data.

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?

"Use before tb_search when you need a category id, a brand id, or the exact attribute slugs and values" gives an explicit sequencing rule and trigger conditions. What is missing is any exclusion — nothing tells the agent when to call tb_category or tb_brands instead of this tool.

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