replay_execution

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

The description discloses key behavioral traits: it re-runs with same target, byte-exact original payload, same credentials, fresh attempt counter. It states it is deliberately not idempotent and only works for terminal (SUCCEEDED or FAILED) executions. Since no annotations are provided, these details are critical and well-provided.

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 two sentences that efficiently convey everything needed. No wasted words; front-loaded with core action.

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 the tool simplicity (single parameter, no output schema, no nested objects), the description covers purpose, constraints on input, behavioral implications, and even distinguishes from siblings implicitly via context. No critical gaps.

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 covers the parameter with minimal description. The tool description adds the requirement that the execution must be terminal (SUCCEEDED or FAILED), which is beyond the schema and adds semantic value. With 100% coverage, description provides meaningful additional context.

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 uses the specific verb 're-run' and identifies the resource as 'terminal execution'. It clearly states the tool creates a brand-new execution with the same target and payload, which distinguishes it from the sibling get_execution (read) and get_usage (read).

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 explicitly states this is the 'outage-recovery path' and that failed calls can be re-executed without regenerating payload. It also warns that each call creates a new execution and is not idempotent, guiding the user on when to use and the side effect. However, it does not explicitly exclude use cases like modifying the payload.

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