Save Incrementality Test Design

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

Far exceeds the annotations: it discloses idempotency semantics, HTTP status codes (201/200), the specific 409/403 refusal reasons, required scopes (create:models, project write/owner), and the crucial behavioral caveat that a planned record has no measured lift and cannot calibrate a model. No contradiction with the declared hints.

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?

Dense and front-loaded, with the return shape and idempotency up front and refusals/permissions trailing. It is a single long paragraph, so a reader must parse carefully, but nearly every clause carries actionable information.

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?

Complete for a mutation tool: prerequisites, defaults, refusal modes, permission requirements, idempotency and the no-lift limitation are all covered. Return values are described even though an output schema exists, and the sibling relationship to get_incrementality_test is called out.

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?

With 0% schema coverage the description must carry the load, and it does: it explains that only project_id (defaulting to the model's project, 400 when neither exists) and an optional name are sent, and that the record body is built server-side from model_hash/calculation_id. It stops short of documenting the format of model_hash and calculation_id explicitly.

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 precise verb and resource ('Turn an available test-design result into a planned incrementality test record in the registry'), and the surrounding detail (type time_holdout/geo, status planned, source.tool design) makes it clearly distinct from create_incrementality_test, design_incrementality_test and get_incrementality_test_design.

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 precondition (an available test-design result) and explicitly bounds scope ('nothing here launches an experiment or changes a budget'), plus refusal conditions. It stops short of naming which sibling to use when the result is not yet available, so an agent must infer the alternative from the refusals.

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