Search Records

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

Annotations only declare readOnlyHint=true; the description adds real value beyond that by naming a hard failure mode (wrong index type) and eventual-consistency lag on newly upserted records, plus the hit shape (_id, _score, fields). That is useful operational context, but it doesn't discuss limits such as topK cost, filter-field pitfalls, or rerank interaction, which the schema carries instead.

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?

Front-loaded with the core action, then prerequisites, alternatives, return shape, and the consistency caveat in a logical order. It runs long and packs four distinct clauses into one sentence with em dashes, which slightly hurts scannability, but no sentence is wasted.

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 no output schema, the description does describe the returned hits, and it covers the two biggest failure risks (index type and indexing lag). Remaining gaps, such as topK/latency tradeoffs and rerank usage, are covered by the schema, so an agent has enough to call it correctly.

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% and the nested query/rerank/filter objects are thoroughly documented there (including filter operator syntax and rerank model choice). The description adds no parameter-level guidance of its own, so the baseline of 3 applies.

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 ('search an index for records that are semantically similar to the query text') and scopes it to integrated-inference indexes. It explicitly names the sibling it is not (search-document-index) and the sibling used to verify applicability (describe-index), so an agent can route 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?

Gives an explicit precondition (only works on integrated-inference indexes), the failure mode on standard/document indexes, the alternative tool to use instead, and the diagnostic tool to check index type. Also covers the retry case for freshly upserted records. This is about as complete as when/when-not guidance gets.

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