evaluate

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

No annotations are provided, so the description carries the full burden. It discloses the core behavior (running benchmark scenarios and reporting metrics) but does not mention potential side effects, performance implications, or prerequisites such as whether an index must be built first. This is a modest gap for a benchmark tool.

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 but efficiently packs two logical parts: the scenarios covered and the metrics reported. It is front-loaded with the main action and contains no fluff or redundant phrasing.

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?

Given the tool has no parameters and no output schema, the description adequately explains what it does and what it returns (metrics list). It could further clarify whether output is a JSON object or if any setup is required, but overall it is contextually sufficient for a complex tool.

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 tool has zero parameters, and the schema property list is empty, so there is no parameter information to add. The description correctly omits parameter details, which is appropriate for a tool with no inputs. Baseline for 0 params is 4.

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 the tool runs a built-in real benchmark harness across specific named scenarios (small, medium, monorepo, polyglot, ignored-tree, broken-state, rename-freshness) and reports concrete metrics. This specific verb+resource combination distinguishes it from sibling tools like 'validate_index' or 'search'.

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 when to use the tool: for benchmarking accuracy, validation rates, freshness reliability, and latency. While it doesn't explicitly name alternative tools or exclusions, the context is clear that this is for evaluation/measurement, not for direct operations like indexing or searching.

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