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

Annotations only declare the safety profile (non-readOnly, idempotent, non-destructive, closed-world); the description adds the substantive behavior: no upstream acquisition, replay-enablement requirement, retention requirement, that replay never becomes live, and that approval must happen through the dashboard_url in a signed-in browser rather than via this 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?

Front-loads what the tool does and the no-upstream-acquisition fact, then covers preconditions and the return shape in a compact block. The closing sentence about approve_full_run and PREVIEW holds is a slight digression but earns its place as sibling routing.

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?

With no output schema, the description helpfully enumerates the return shape ({run_id, status, mode, version, dashboard_url}) and covers prerequisites and the non-live/non-approving nature of replay. The only meaningful gap is the absence of any parameter-level semantics for three undocumented required inputs.

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% and none of the three required parameters (recipe_id, recipe_digest, sources_from_run) is explained in the description. The phrase 'a named successful run of the same table' loosely maps to sources_from_run, but the recipe_id/recipe_digest pair is left entirely undefined, so the description fails to compensate for the coverage gap.

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 (Runs) and resource (a registered recipe revision) against a precisely scoped input source (retained raw inputs of a named successful run of the same table). The clause 'No upstream acquisition is performed' implicitly separates it from start_run, so an agent can distinguish it from siblings without opening their schemas.

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 explicit preconditions ('Replay must be enabled and the inputs must still be retained') and steers the agent away from a wrong action ('Replay never becomes live and does not approve a repair', with approve_full_run handling a different hold type). It stops short of naming the tool to use when replay is not enabled or inputs are gone.

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