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

Goes well beyond the annotations (which only say it's a non-readonly, non-idempotent, non-destructive mutation) by explaining timing ('takes effect on the next SDK request'), the enrollment-only effect ('already-enrolled units keep their group... evicts no one'), and that group weights never change. It also discloses the reason field is 'shown to the approver', which has real workflow consequences.

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-loads the core action and keeps the essential safety facts in a compact paragraph. It is dense but nearly every clause earns its place; the only slight redundancy is restating the action semantics that the schema already documents.

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 an 8-parameter mutation with no output schema and no destructive flag, the description supplies what's needed: side effects, timing, prerequisite skill, confirmation requirement, and the fact that existing assignments are unaffected. Nothing an agent needs to call it safely 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 88%, so the baseline is 3, but the description adds framing beyond the schema: the exact-name-as-confirmation contract, the reason-for-reviewer purpose, and the clarification that lowering or pausing only halts new enrollment. The action mapping largely echoes the enum's own description, which limits the added value.

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?

Uses a specific verb and resource ('Change a scheduled or active experiment's staged rollout') and enumerates the concrete operations (set, advance, pause, resume, replaceSteps). This clearly distinguishes it from siblings like terminate_experiment or preview_experiment, which handle different lifecycle operations.

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?

Gives a clear prerequisite ('Load the experiment-rollouts skill first') and requires the exact name from get_experiment as confirmation, which routes the agent to get_experiment before calling. It doesn't explicitly contrast with alternatives (e.g., terminate_experiment for stopping entirely), so it stops short of full when/when-not coverage.

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