careers_filters

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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description adds a concrete behavioral statement that the returned filter options are not hardcoded but live, and that query requires a minimum length for autocomplete. This gives the agent expectations about dynamic results and input constraints. No contradictions with annotations.

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 three sentences, front-loads the core purpose, then provides usage guidance and a key constraint. Every sentence adds relevant information without fluff or repetition. It is concise and easy to parse.

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?

The output schema exists, so return values are covered. However, with five optional parameters and no schema descriptions, the description leaves gaps: the role of the `entity` parameter is completely absent, and the exact meaning of `field` is only implied. The 'start here' workflow hint is useful but the description doesn't fully specify how to use the tool alongside search tools. It is adequate but not complete.

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?

The schema has zero descriptions for its five parameters, so the description must compensate. It adds some meaning for the `query` parameter (2+ characters for autocomplete, exact labels/IDs preferred) and implies the `field` parameter selects the filter for which accepted values are returned. However, the `entity`, `limit`, and `offset` parameters are not explained, and even the relationship between `field` and `entity` is not stated. Overall, it provides partial but not sufficient parameter coverage.

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 identifies the tool as a read-only discovery mechanism for career filters and accepted field values, using the specific verb 'Discover' and the resource 'live filters / accepted values for field.' It distinguishes itself from sibling search tools by positioning itself as a prerequisite ('Start here before career searches') and by mentioning autocomplete capabilities. However, the 'or' phrasing slightly muddies whether it returns all filters or values for a single field.

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 explicitly instructs the agent to use this tool before performing career searches, giving it a clear temporal placement in a workflow. It also provides a rule for autocomplete behavior ('needs query (2+ characters)') and recommends exact labels/IDs to avoid ambiguity. It doesn't explicitly name sibling alternatives, but the 'start here' directive provides sufficient guidance for selecting this tool.

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