compare_run_sets

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds a meaningful behavioral trait not in annotations: the operation is a non-persistent preview of compatible frozen cohorts. It doesn't discuss errors or auth, but the annotation coverage lowers the bar.

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?

One sentence, front-loaded with the core action and the no-persistence caveat, then the routing instruction. No filler or repetition of the schema.

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?

The description is sufficient for selecting the tool and understanding its non-persistent nature, and the output schema reduces the need to describe return values. However, given the oneOf request union and many required fields, it leaves the criteria for 'compatible' and how to choose between request variants mostly to the schema. A mid-range score is appropriate.

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 0%, so the burden falls on the description, which only contributes the domain constraint 'frozen cohorts.' It does not explain the required baseline/candidate run-set IDs, polarity, practical threshold, metric, unit, or the measurement-vs-runtime-resource union choice. Thus it adds minimal value over the schema.

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 action ('Preview') on a specific resource ('compatible frozen cohorts') and explicitly distinguishes itself from record_comparison by noting it does not persist. This is more than a restatement of the tool name and lets an agent tell it apart from the recording sibling.

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 frames the intended use as a dry-run/preview and names record_comparison as the tool to use when persistence is wanted. This gives the agent an actionable when/when-not rule, although it doesn't enumerate other comparison siblings like compare_artifact_pipelines.

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