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

Annotations already declare readOnly, idempotent, closed-world, non-destructive behavior, so the bar is lower. The description still adds real context beyond them: tenant scoping, ranked-result semantics, mode selection, and the doc-grouped result shape that differs from chunk-level retrieval; it doesn't cover pagination interaction with limit/offset or refusal behavior (the schema does).

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 sentences, front-loaded with what the tool does, then mode summary, then routing guidance. 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?

With annotations covering safety, a full schema, and an output schema, the description supplies what's missing: purpose, result shape, and sibling routing. It leaves limit/offset paging behavior implicit, a minor gap given the schema documents those fields.

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 the baseline is 3. The description's only parameter-related content is restating the three modes, which the schema enum and its description already document, so it adds no meaning beyond structured data.

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 and resource (hybrid keyword+vector search across documents) plus scope (caller's tenant) and output shape (ranked results with snippets). It explicitly distinguishes itself from kb_chunks_retrieve by noting this tool returns doc-grouped results for browse/search UIs, so an agent can pick between the two without opening schemas.

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?

Names a concrete alternative and the condition that selects it: passage-level grounding goes to kb_chunks_retrieve, document browsing goes here. It doesn't address other plausible siblings (kb_documents_list, kb_skills_search), so it is clear but not exhaustive.

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