Rerank Documents

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

readOnlyHint=true already tells the agent this is a non-mutating operation, so the safety profile is covered by annotations. The description adds a genuine scoping constraint (only for documents not already retrieved from an index), but says nothing about result behavior — how the reranked output is ordered, whether scores are returned, or what happens if topN exceeds the document count.

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?

Three sentences, front-loaded with the core action, followed by the input constraint and then the routing alternative. Every sentence carries decision-relevant information; nothing is redundant with the title.

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 6-parameter read-only tool with a nested options object, the description covers purpose and correct tool selection well, and the schema handles parameter detail. The one material gap is the return format, which matters because there is no output schema — the agent is not told that documents come back reordered or with relevance scores.

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 83%, so the schema already explains model enum trade-offs, rankFields constraints, and the llm_model/llm_provider analytics fields. The description adds no additional parameter meaning beyond that, which is the expected baseline 3 when structured fields carry the load.

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 ("Rerank a set of provided documents by relevance to a query") and immediately bounds the input domain to documents that did not come from a Pinecone search. An agent can distinguish it from search-records and the other index-scoped siblings without opening a 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 an explicit use case (externally sourced text) and an explicit alternative with the condition that selects it: for single-index search results, use the "rerank" parameter of search-records instead. This is exactly the when/when-not/alternative structure the dimension asks for.

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