evaluate_retrieval

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

With no annotations available, the description carries the behavioral burden. It conveys that the tool is observational/read-only through 'measure' and 'quantify,' and clarifies it consumes labeled cases rather than modifying documents. It does not spell out side-effect absence or output shape, but the evaluation framing is non-mutating and sufficient.

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 short sentences front-load the action and metrics, then add the case format and purpose. No filler or repetition of schema defaults.

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?

The description is adequate for choosing the tool and constructing the required cases, and it names the metrics returned. However, with no output schema and no annotations, it could usefully state how mode/topK/collection affect the evaluation and that it requires a populated collection.

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 must compensate, but it only explains the required 'cases' parameter ('Each case is {query, relevantSources}'). It adds no meaning for mode, topK, or collection, leaving their semantics to be guessed from names and defaults.

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 ('Measure') and a precise resource ('retrieval quality on labeled cases'), then names concrete metrics: hitRate, mrr, recallAtK. This clearly separates it from sibling tools like search (retrieval) and answer (generation).

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?

It explicitly says 'Use it to quantify quality and catch regressions,' giving a clear context for invocation. It does not name when-not-to-use alternatives, so it falls just short of the highest bar.

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