textSearch

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds behavior the structured fields don't: results are returned best-first with a __score field, `total` reflects the full match count rather than the returned page, and matching is done over a text index with the pre-ranking filter scope. Sorting/return semantics are disclosed, though pagination behavior is left to the schema.

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 dense sentences with no filler: the first gives mechanism, ordering, filter scope, and the meaning of `total`; the second is a compact operator reference. Information is front-loaded and every clause carries distinct meaning.

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 an output schema present and 100% parameter description coverage, the description need not restate return shapes, and it still adds ranking/count semantics. The only real gap is that it does not tell the agent how this interacts with the other search tools or how skip/limit behave across the `total` count, which an agent choosing among many search siblings would benefit from.

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 100%, so the parameter baseline is 3, but the description goes beyond the schema by explaining query operators (any vs all under allTerms, quoted phrases, '-' exclusion, '+' requirement) that the schema only gestures at as 'Keywords to match'. It also clarifies the interaction of `labels` and `where` as the pre-ranking selection scope.

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 ('Keyword (BM25) search over a text index') and the ranking semantics ('best first (__score)'), which cleanly separates it from semanticSearch/vectorSearch by mechanism. It does not name those siblings or smartSearch explicitly, so an agent must infer the contrast from the word 'Keyword'/'BM25' rather than being told.

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?

Usage is implied by the mechanism – lexical/BM25 matching is what this tool is for – and the query syntax hints at when the advanced options apply. However, there is no explicit when-to-use, when-not-to-use, or named alternative (semanticSearch, smartSearch) to route the agent among the several search tools listed as siblings.

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