Get Incrementality Test

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavioral context beyond them: the calibration success vs. refusal shape, the enumerable refusal reasons, and the required read:models scope. This is unusually rich disclosure for a read tool.

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 but front-loaded: purpose first, then version, then the model_hash/calibration branch, then refusal handling and scope. Every clause carries meaning, though the inline brace-listing of base record fields is somewhat redundant against the output schema and adds bulk.

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 read tool with a required scope, a rich conditional output (calibration), and five params at 0% schema coverage, the description supplies everything needed: id/version semantics, the model_hash branch, refusal enumeration, and cross-tool linkage. With an output schema present, it need not do more.

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 0%, so the description must carry the load, and it does: version (older version, default current), model_hash (a saved model you can read, triggers calibration), channel (a model activity column, passed for channel_not_in_model), and confirm_kpi (pass true only if the test's outcome really is the model's KPI). Four of five params are given real semantics.

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+resource ('Read one recorded test') and enumerates the record shape ({id, version, record, content_hash, used_by, retired_at}), which cleanly distinguishes it from the sibling list_incrementality_tests (singular fetch vs. list). An agent can pick this tool without opening another 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?

Gives clear usage context: version reads older versions (default current), model_hash enriches the result, and refusals are answers not errors with named remediations. It cross-links to create_model(calibration={tests: [...]}). It stops short of an explicit 'when-not/what-alternative' statement (e.g. pointing to list_incrementality_tests to find ids), so not a full 5.

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