Get Filters

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description adds real domain behavior beyond that: the shape of returned filters, the three kind semantics, and the dependency rule that forces a follow-up call to get_options. It doesn't mention pagination or max_options truncation behavior, keeping it from a 5.

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?

Three compact lines, front-loaded with the primary deliverable, then the kind mechanics, then the dependency caveat. Every sentence carries distinct information with no filler.

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?

An output schema exists, so the description is not obligated to document return values, yet it supplies the domain conventions (kind variants, depends_on_feature) that an agent needs to interpret them and chain into get_options. Complete for its complexity, with only minor omissions like truncation behavior.

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 both inputs (category, max_options) are already documented in the schema and the description adds nothing about them. The field names discussed (option_ids, feature_id, min/max, unit) are output-side concepts, not input parameters, so per the baseline this is a 3.

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?

States a specific verb+resource — filters available in a subcategory — and names the concrete payload (feature ids and option ids) the agent will retrieve. It also distinguishes itself from the sibling get_options by calling out dependent features (city after region, model after brand), so an agent can route correctly without opening either 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?

The kind='options'/'range'/'flag' breakdown explains how each returned filter variant is consumed, and the depends_on_feature note routes the agent to get_options. It stops short of stating when to call get_filters versus categories or search in the first place, but the guidance present is concrete and actionable.

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