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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds real behavioral value beyond that: it discloses the composite/aggregated nature of the output (deltas, per-criterion decomposition, judge reasoning) and gives interpretive guidance on failure clustering.

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-loaded with the core purpose and the 'with receipts' framing, then progresses through outputs, usage trigger, and diagnostics in a logical order. Dense but each clause carries information; slightly verbose with the long colon-separated inventory, keeping it from a 5.

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?

With no output schema, the description must carry the return-value burden, and it does so thoroughly (eval coverage, run history, per-criterion averages, deltas, judge reasoning). Combined with the 100% schema coverage on inputs, an agent has everything needed to call and interpret it.

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 flowId and workspace are already documented in the schema. The description adds no additional semantics about the parameters themselves (its 'runId' mention is about output citation, not an input). 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+resource ('how a Workbench flow is actually doing') and enumerates the exact contents of the report: eval coverage, recent runs with scores, per-criterion averages, delta vs previous run, and worst items with judge reasoning. This distinguishes it clearly from raw siblings like caliper_evals_runs_list or caliper_evals_runs_get.

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 an explicit trigger ('Use this BEFORE claiming a flow works or proposing changes') and a follow-through requirement (cite runId + scores). It also explains how to interpret worst items diagnostically. It does not name alternative sibling tools (e.g., evals_runs_list for raw run data), 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.