rerank

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

With no annotations, the description is the sole source of behavioral information. It only states the basic action and does not disclose what the output looks like (e.g., ordered list with scores), whether the operation is read-only, or any rate limits or error conditions. This is minimal and leaves the agent with little expectation of behavior beyond the bare operation.

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 a single sentence, efficient and immediately front-loaded with the key verb and object. The trailing '/rerank' is slightly redundant but not confusing. It earns a high conciseness score, though it could be even cleaner without that detail.

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 and no annotations, the description should explain the return value (e.g., reranked document order and scores) and any contextual prerequisites. None are provided. For a 4-parameter tool, this sparse description leaves the agent uncertain about the expected result, making it incomplete.

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?

The schema descriptions cover all parameters with 100% coverage, so the baseline is 3. The description adds no additional meaning beyond the schema, neither clarifying top_n semantics nor providing examples. It does not harm comprehension but contributes no extra value.

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 uses a specific verb 'rerank' and identifies the resource (documents) and the query criterion. It clearly distinguishes this tool from siblings like chat_completion or create_embedding, none of which mention reranking. The reference to LiteLLM adds implementation context without obscuring the primary purpose.

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 implies the tool is for reranking documents against a query, but it does not explicitly state when to use it versus alternatives or provide exclusions. No prerequisites or typical invocation scenarios are mentioned, leaving usage context implied rather than explicit.

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