retry_run

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

No annotations are provided, so the description carries the full behavioral burden. It reveals the basic outcome—starting another attempt—but does not disclose side effects, whether the previous attempt is affected, permissions needed, or whether the operation is reversible. For a tool that mutates run state, this is a meaningful gap.

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?

The description is a single short sentence with no wasted words. It is front-loaded with the core idea before the qualifier. It sacrifices richness for brevity, but as a pure structural matter it is concise and readable.

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?

Given a single required parameter and an output schema, the tool is not highly complex, but a retry action has important ambient behavior. The description does not explain when retrying is allowed, what happens to the existing run, or whether it can be safely invoked. This leaves an agent without enough context to confidently invoke the tool in a nontrivial incident.

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?

The schema description coverage is 0%, and the description never mentions process_instance_id. It only refers to 'a run,' which loosely implies the parameter identifies the run to retry, but there is no explicit mapping. Since the description must compensate for the schema's silence and does not, parameter semantics are weak.

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 clear action—give a run another attempt—and qualifies the target as one 'stuck on an incident.' This distinguishes it from list/get/cancel operations at a basic level, though it does not name a sibling tool explicitly. The phrasing is slightly awkward but still conveys that this is a retry operation.

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 implies when to use the tool ('a run that is stuck on an incident') but gives no explicit guidance about when not to use it, such as for runs that failed normally or are already canceled. It also does not mention alternatives like cancel_run or get_run. Context is present but chosen exclusions are not.

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