eval

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

With no annotations, the description carries the full burden and does well: it discloses that the tool is indexless (never builds), consumes only the existing index, and that min_ndcg drives a non-zero exit — i.e. it can fail. It omits behavioral traits like runtime cost or idempotency, so it is strong but not exhaustive.

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?

Four sentences, all substantive: action, indexless precondition, CI intent, and the MCP json default lead in order of importance. Slightly dense with parentheticals, but nothing is pure filler.

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 four-param, no-output-schema tool with no annotations, the description covers action, deliverables, dependency ordering, failure semantics, and a default divergence between MCP and CLI. There is no output schema, but the return shape (per-query and aggregated metrics as EvalReport JSON) is named.

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 100%, so the schema already documents all four parameters, including the MCP-vs-CLI default for `json`. The description's parameter remarks largely restate schema content, so the baseline 3 applies.

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 ("Run the ranking-quality harness against a golden query set") and enumerates the exact outputs (nDCG@10, recall@10, MRR). This clearly separates it from sibling tools like `index`, `tests_for`, or `check`.

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 explicit context ("Intended as a CI regression guard") and a prerequisite ("run `index` first if missing"). It lacks an explicit when-not-to-use or a direct comparison against a sibling such as `check`, so it falls just short of a 5.

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