search_rerank

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

Annotations already establish that this is read-only and non-destructive, so the description does not need to restate that. It adds useful behavioral context by naming the pipeline two stages and a key price/latency. This goes beyond the structured annotations and helps an agent understand operational trade-offs.

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?

The description is concise: two sentences, no filler, no repetition of schema or annotations. The mechanism is described first, then the usage policy, so the most identifying information is front-loaded.

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 read-only search tool with an output schema, this is mostly complete: the agent knows what happens and when to use it, and the output returns is already covered by the schema. It loses a point because the description does not clarify the precise meanings of several parameters, meaning an agent might still guess on limit versus rerank_top_n.

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 0%, so the description is expected to compensate for the parameter semantics. It only gives a general sense of 'top results', which loosely hints at the role of limit and rerank_top_n, but does not clarify how filters, collection, limit, or rerank_top_n individually behave. The meaning of rerank_top_n, in particular, remains ambiguous.

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?

The description clearly states a specific operation: hybrid search followed by cross-encoder reranking. It also communicates the value proposition, maximum precision at extra latency, making it easy to distinguish from sibling tools.

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?

The description explicitly provides an when-to-use rule: use it when result quality matters more than speed. It also gives a counterexample ('exploratory search') to discourage misuse, making the selection criteria clear even without naming specific alternatives.

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