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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the agent knows this is a non-read, non-destructive, non-idempotent operation. The description adds valuable behavioral context beyond annotations: it returns the exact list of differences, it does NOT apply the change, and it is a proposal/preparation step. It doesn't describe side effects like whether a proposal record is persisted, but the 'Stored with the proposal as its record' note in the request parameter partially covers that. With annotations carrying the safety profile, a 4 is appropriate.

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?

Three sentences, each earning its place: the first states the core behavior and return value, the second gives the required human-in-the-loop workflow, the third gives the prerequisite call. The most important constraint (WITHOUT applying it) is front-loaded. Zero waste.

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 proposal tool with 6 params, 100% schema coverage, and no output schema, the description covers the critical workflow context: what it returns (diff list), what to do with it (show to person), and what to call before/after (describe_configuration/apply_configuration). It doesn't describe the output format of the diff list, but the description explicitly says 'Returns the exact list of differences' which is sufficient for an agent to know what to expect. The nested objects are documented in the schema. A 4 is appropriate – complete for the agent's decision-making needs.

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%, so the schema already documents all 6 parameters. The description adds one meaningful cross-parameter constraint: 'Call describe_configuration first so the keys are real' – which tells the agent that settings and labels keys must come from describe_configuration. However, it doesn't explain the nested structure of layouts or branding beyond what the schema already provides. Baseline 3 is correct when the schema does the heavy lifting.

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 states a specific verb ('Prepare'), a clear resource ('a change to how the locator looks or behaves'), and an explicit non-goal ('WITHOUT applying it'). It also distinguishes itself from apply_configuration by naming the sibling and the exact relationship. This is a model of purpose clarity.

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 description gives explicit when-to-use guidance: call describe_configuration first so keys are real, and show the returned diff list to the person and get agreement before calling apply_configuration. It names the alternative tool and the sequencing condition. Nothing is left to inference.

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