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

Annotations already declare readOnlyHint and idempotentHint, but the description goes well beyond them: it enumerates the classes of blocking problems (bad weights, stale baseValue, missing paths, name taken, invalid targeting, paths locked by another experiment), explains that each change is returned with the base configuration's current value, and flags `exclusionConflicts` as non-blocking with an instruction to surface it to the user.

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?

The core behavior and the create_experiment contrast are front-loaded, and no sentence is pure filler. The parenthetical problem list and the exclusionConflicts clause are dense but each carries distinct information; the skill-loading note could arguably move to a separate line rather than trailing the sentence.

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?

There is no output schema, so the description must explain returns, and it does: validity verdict, blocking problems, per-change base values, and exclusion conflicts with their blocking status. What remains underspecified is the exact shape of the response (e.g., how changes are keyed per group), but the actionable content is complete for a dry-run tool.

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 67% with a deeply nested object whose leaf fields are already annotated, so the schema carries most of the burden. The description adds one useful cross-reference, that `experiment` is identical to create_experiment's argument, plus an indirect signal about `baseValue` via 'stale baseValue', but gives no detail on projectId or environment beyond what the schema states.

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?

The opening sentence names a specific verb and resource ('Dry-run an experiment definition without creating anything') and immediately ties it to the sibling it mirrors ('Takes the same `experiment` object as create_experiment'). An agent can tell this apart from create_experiment and preview_configuration_change without inspecting 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?

Explicit routing: use it before create_experiment, note that create_experiment runs the same checks but mutates, and an alternative use case (show the user the plan first). It also states a prerequisite action, loading the manage-experiments skill, so the agent knows setup is required before calling.

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