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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is covered. The description adds real value by identifying what is applied (the frozen variant snapshot) and to what (the agent), but it omits whether the agent's current configuration is overwritten and whether the promotion is reversible.

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?

A single front-loaded sentence with the verb, scope, precondition, and mechanism in that order. No filler, no redundancy with the title.

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 destructive mutation with no output schema, the description covers what happens but not the side effects an agent should anticipate (overwriting the live agent configuration, whether the change can be undone). With annotations covering the safety profile, this is adequate but leaves clear gaps.

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%, including the superadmin-only note on customerId, so the schema carries the semantic load. The description adds no parameter-level detail (e.g., format of productionTestId or when customerId should be supplied), so the baseline of 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 (promote) and resource (production A/B test) and adds the mechanism — applying the frozen variant snapshot to the agent. It does not, however, distinguish itself from nearby siblings such as rollback_production_test or apply_variant, which an agent may confuse it with.

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?

The word 'decided' implies a precondition (the test must already have a decision/outcome) before promotion is valid, which is useful implied guidance. There is no explicit statement of when not to use it, nor a named alternative such as rollback_production_test for undoing a promotion.

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