Search the company knowledge base

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful behavioral context by noting that results come from the same retrieval path Mira uses for visitor answers, which sets expectations about result semantics without repeating annotation data.

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 sentences with no filler. The core action, retrieval semantics, and intended use case are front-loaded, and every clause contributes useful information.

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?

Given the simple two-parameter schema, strong safety annotations, and presence of an output schema, nothing essential is missing. The description clearly explains what the tool does, why an agent would call it, and how it relates to Mira's retrieval 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?

The schema documents k well ('Chunks to return, default 5') and query minimally as a string. The description adds meaning by indicating the query should represent a visitor-style question used to validate grounded coverage, compensating for the low schema coverage on the query parameter.

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 ('search'), specific resource ('knowledge base'), and a distinctive mechanism ('semantic search using the same retrieval Mira uses for visitor answers'). It also frames the exact use case, validating grounded coverage before launch, which distinguishes it from the sibling answer_visitor_question.

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?

Clearly positions when to use the tool: before launch, to validate grounded coverage for a question. It does not explicitly name alternatives or exclusions, so it falls short of a 5, but the context is concrete enough for an agent to infer appropriate use.

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