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

Annotations only cover the safety profile (readOnly=false, destructive=false, openWorld=true); the description adds substantial context beyond them — the run is long-running and re-enters THIS conversation automatically on completion, it consumes workspace LLM budget, and it may return a `needs_confirmation` envelope behind an approval gate. That is exactly the behavioral detail an agent needs to avoid polling or misreporting.

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 action and well organized, but the mid-section sentence about auto-return, budget, and approval is dense and runs long. Nearly every sentence earns its place, so it stays efficient despite the density.

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 compensates by explaining that the scores arrive via an automatic follow-up in this conversation, plus the approval-gate response shape. For a cost-bearing async mutation tool, nothing essential for a correct call 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 description coverage is 100%, so all four parameters (evalId, label, workspace, approvalId) are already documented in the schema; the description's mention of the approval gate loosely motivates approvalId but adds no syntax or format detail. Baseline 3 applies when the schema carries the parameter documentation.

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 — 'Queues a new run of an eval' — and immediately defines the operation as inference over the dataset followed by LLM-judge scoring. It is clearly distinguishable from siblings like caliper_evals_runs_get, caliper_evals_runs_list, and caliper_evals_runs_cancel.

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?

Explicitly positions the tool as 'THE VERIFY STEP of the improvement loop' and gives the trigger condition: after an approved workbench_flows_edit_text, run the eval again and report the score delta. It also tells the agent not to poll and what to tell the user, which fully closes the usage loop.

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