search_corpus

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

With no annotations, the description carries the load and does disclose two non-obvious traits: results are threshold-filtered and policy gating is intentionally skipped. It does not cover safety profile, ordering, or pagination behavior, but the policy-gate disclosure is the highest-value piece an agent could not infer.

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 short sentences, zero filler, with the core capability front-loaded and the routing caveat placed last where it is most actionable. Every sentence earns its place.

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?

No output schema and no annotations, so the description is the only specification available; it covers return content in outline and the policy-gate behavior, but leaves the two tuning parameters and any notion of result ordering or result-count control undocumented for a 3-param tool.

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 0% across three parameters, so the description must compensate and largely does not: max_passages and include_below_threshold are never explained, and the 'retrieval threshold' concept that makes include_below_threshold meaningful is only alluded to. Only the query concept is implicitly covered.

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?

Specific verb + resource ('Lexical search over the approved corpus') plus a scope statement ('Returns passages above the retrieval threshold with full citation metadata') that separates it from the semantic/QA siblings. An agent can distinguish it from answer_question and get_passage without opening any 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?

Explicitly states a negative condition ('Does NOT run the policy gate') and names the correct alternative with the selecting condition ('use answer_question for user-facing questions'). This is exactly the when/when-not/alternative structure that routing requires.

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