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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), yet the description adds real behavior: the default returns only the ten lowest-scoring items, works for both Caliper-run and CI-submitted runs (triggeredBy 'ci'), and the no-polling rule. This goes meaningfully beyond what the annotations declare.

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 shape before the motivational framing, and each sentence carries information. The emphatic 'THE ANSWER' phrasing is slightly promotional but not wasteful.

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, and the description fully compensates by describing the returned fields (status, score, per-criterion scores, judge reasoning) and the item-selection modes. Nothing an agent needs to call and interpret it is missing.

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 coverage is 100%, so the schema already documents every parameter including the items enum and limit default. The description reinforces the items default ('by default the ten lowest-scoring items') but adds no syntax or format detail beyond the schema, so 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 (read/get) and resource (one eval run) and enumerates the payload: status, overall score, per-criterion item scores, judge reasoning. An agent can distinguish it from caliper_evals_runs_list (listing) without opening either 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 explicit triggering context ('THE ANSWER to why did the score drop', 'read it when the user asks') and a when-not constraint ('Still no polling loops'). It does not name a sibling alternative like caliper_evals_runs_list for the opposite case, so it stops short of full routing guidance.

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