deep_search

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

Annotations only declare readOnlyHint=true, so the description carries the rest and does add real operational detail: parallel subquery execution, clustering, and deduplication of merged chunks, which tells the agent the output is a fused result set. It omits cost/latency implications of a multi-hop run, which matter for an expensive operation, so it stops short of full disclosure.

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 the core capability front-loaded and no filler. The internal-mechanism clause (cluster/merge) is somewhat packed but each part 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?

An output schema exists, so return values need not be described, and the description conveys the overall pipeline. However, with five undocumented parameters and no explicit usage boundary against siblings, it is only minimally sufficient for correct invocation.

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% and none of the five parameters (alpha, rerank, sub_queries, top_k_per_subquery) is explained. The mention of 'subquery searches' loosely gestures at the sub_queries parameter but gives no semantics for any field, so the description fails to compensate for the coverage gap.

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+resource: multi-hop search that decomposes complex research questions and merges deduplicated chunks. The 'multi-hop' framing implicitly distinguishes it from the plain 'search' sibling, but it never names that alternative explicitly, so the differentiation is left to inference.

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?

'Complex research questions' implies the usage context and contrasts with simple lookups, but there is no explicit when-to-use/when-not-to-use statement and no reference to the sibling 'search' tool. An agent must infer that lighter queries should go elsewhere.

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