search_spec

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

With no annotations, the description fully discloses key behaviors: case-insensitive literal matching, max_results cutoff, the meaning of allow_errors, the 'unsupported' flag and its implications for run_verification vs run_xml_verification, and the active spec resolution. This goes well beyond a simple summary.

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 organized into clear sections: purpose, matching behavior, result fields, unsupported note, and active spec context. Each sentence adds information without redundancy; it is appropriately sized for a tool with no output schema.

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 description covers output structure (result fields, status), edge cases (unsupported), and environmental dependence (active spec), which is sufficient for an agent to invoke correctly. There is no output schema, so this level of detail is necessary and 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?

Although the schema only provides titles, the description explains query as a natural-language string matched against name, description, or category, and max_results as the cap on returned results. It also clarifies the language requirement, which is not evident from the schema.

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?

Clearly states 'Search the loaded QA spec for conditions matching a natural-language query.' It specifies the resource (QA spec), the action (search), and the output type (conditions). The subsequent details about literal substring matching and language support further distinguish it from sibling tools like list_conditions.

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 the search semantics (literal substring, not semantic) and notes the active spec selection behavior, giving users context for when to invoke it. It does not explicitly name alternatives, but the behavior description implies it is for finding specific conditions, as opposed to listing or describing.

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