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

Adds substantial behavior beyond the annotations: the event is re-read from the app, event data is never stored, a new run is created on the pinned version, the retry is billed like any run, and the automation's actions (e.g., replying to an email) execute again. That last point is critical side-effect disclosure for a non-idempotent, open-world mutation.

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?

Two dense sentences, front-loaded with the action and immediately followed by mechanics and constraints. The parentheticals earn their place, though the first sentence is long enough that it takes a second read.

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 one-parameter mutation with no output schema, the description covers preconditions, billing, data handling, and side effects. An agent has everything needed to decide whether to call it and what the consequences are.

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 run_id is already documented as 'a finished run an automation started, like run_…'. The description reinforces the eligibility constraint but adds no format, sourcing, or lookup guidance beyond the schema, so baseline 3 applies.

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 and resource ('Runs an automation run's app event again') and grounds it in a known console action ('like Retry event on the console's run page'). It also clarifies that a new run is created on the automation's pinned version, which separates it from run_workflow for an agent that has both siblings available.

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: only runs started by an active automation can be retried, and only for apps whose events can be read again. That is strong when-to-use framing, but it never names an alternative (e.g., run_workflow) for the cases where retry is not eligible.

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