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

Annotations already declare it is a safe, read-only, non-destructive, closed operation, so the safety profile is covered. The description adds genuine output-shape context: by default returns the ten lowest-scoring items, 'all' is large, 'none' yields totals only, and it works for CI-submitted runs.

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?

Front-loads the return content ('One run: status, overall score...') and stays compact, though the capitalized 'THE ANSWER' aside is slightly editorial. Every sentence carries information about output or usage.

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?

No output schema exists, so the description must convey return values, and it does: status, overall score, per-item per-criterion scores, judge reasoning, and the items/limit default behavior. An agent has enough to call it correctly and interpret the result.

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 baseline is 3. The description restates the items behavior (all/none) that the schema already documents and adds only the 'explain a drop' framing, adding little beyond the structured fields.

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 with scope: reads one eval run, returning status, overall score, and by default the lowest-scoring items with per-criterion scores and judge reasoning. It clarifies the run types it covers (Caliper-run and CI-submitted), though it never names sibling tools like caliper_evals_runs_list to differentiate by task.

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 clear usage context: 'THE ANSWER to why did the score drop — read this, then name the criterion that slipped,' and an explicit exclusion, 'Still no polling loops; read it when the user asks.' It does not name an alternative tool to use instead when the user just wants a run list.

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