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

The annotations only flag destructive and idempotent; the description goes well beyond them by explaining exactly what destruction means: every unit reverts to the base configuration on its next fetch, config path locks are released, and the experiment is permanently unrestartable. It also notes immediate effect and that the reason is recorded with the change, which is precisely the behavioral context an agent needs before an irreversible call.

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?

Effects are front-loaded right after the purpose sentence, which is the correct order for an irreversible operation, and each sentence carries distinct information. The trailing skill-loading instruction is procedural but still earns its place as a prerequisite; the wording is dense but not padded.

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?

For a five-parameter, all-required destructive tool with no output schema, the description covers irreversibility, timing of effect, lock release, and the confirmation parameter contract. It does not describe the response body or failure modes, but nothing essential for correct invocation 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 80%, so most parameters are already documented, but the description adds the intent behind experimentName (an exact-name confirmation guard pulled from get_experiment) and ties reason to the recorded change. The only undocumented parameter, experimentId, is left to the schema, which keeps this just below a 5.

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 description opens with a specific verb and resource ("Stop a scheduled or active experiment immediately") and pins the scope to scheduled or active experiments, which implicitly separates it from update_experiment_rollout or create_experiment. An agent can tell what the tool does without opening the 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?

It clearly states the triggering context (stopping a scheduled or active experiment that cannot be restarted, so a follow-up requires a new experiment) and adds a prerequisite to load the manage-experiments skill first. It stops short of naming the sibling alternative (e.g., update_experiment_rollout) that an agent might confuse it with, so it is strong but not exhaustive.

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