Cascading Search

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

readOnlyHint=true already covers the safety profile, so credit goes to the extra constraints the description supplies: rerank is mandatory and indexes must be integrated-inference. It stops short of noting that reranking adds latency/cost or that topK must exceed topN for the reranker to have candidates — the latter is only in the nested 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?

Four short sentences, front-loaded with what the tool does, then constraints, then the alternative. Nothing is redundant with the title and no sentence is 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?

For a 5-parameter nested tool with no output schema, the description covers the multi-index scope, the mandatory rerank stage, and the index-type constraint. Remaining gaps (what the response looks like, pagination, handling when indexes lack a common schema) are secondary but not fully covered elsewhere.

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% and the nested query/rerank objects carry detailed per-field documentation (topK sizing, filter syntax, rerank model trade-offs), so the schema does the heavy lifting. The description adds only the meta-point that reranking is mandatory, not field-level meaning. Baseline 3.

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 across multiple indexes for records'), plus the pipeline behavior (deduplicate, rerank combined results). It explicitly names the sibling it is not ('To search a single index, use search-records instead'), so an agent can pick between the two without opening either 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?

Gives both the selection condition (multiple indexes) and its inverse (single index → search-records), plus two hard prerequisites: reranking is required and only integrated-inference indexes work. That is the when/when-not/alternative triad.

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