job_rerun

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

Annotations are not provided, so the description must fully carry the burden of behavioral disclosure. The description says 'rerun from its preserved isolated input snapshot,' which clarifies the input source, but it does not disclose side effects (e.g., whether it overwrites output, requires permissions, or is idempotent) or the return behavior. The optional 'wait_seconds' parameter suggests a blocking behavior, but that is not explained. No contradiction with annotations, but significant gaps remain.

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, concise sentence with no redundant wording. It front-loads the primary action and resource. It earns a high score for efficiency, though it could be improved with additional context without violating conciseness.

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?

Despite having an output schema (which could explain return values), the description leaves critical operational details unaddressed: the meaning of 'wait_seconds,' the relation to job state, and how this differs from 'job_resume.' Given the moderate complexity of a rerun operation and the presence of siblings, the description is insufficient for an agent to use the tool correctly without additional inference.

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 the schema only provides type and default for parameters. The description only mentions the 'preserved isolated input snapshot' concept, which relates to 'job_id' but does not explain how 'job_id' is used or what values are acceptable. 'wait_seconds' is entirely ignored in the description, despite being an optional parameter that likely controls blocking behavior. The description fails to compensate for the lack of schema documentation, so this is a significant 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?

The description states a specific verb ('rerun') and resource ('job') and mentions the key concept of an 'isolated input snapshot,' which indicates the tool operates on a preserved snapshot. However, it does not distinguish this from the sibling tools 'job_resume' and 'job_cancel,' so an agent might confuse it with 'job_resume' which also relates to continuing a job. The purpose is clear but lacks differentiation.

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 provides no guidance on when to use this tool versus alternatives like 'job_resume' or 'job_status.' It does not mention prerequisites, such as the job being in a certain state or that the snapshot must exist. No exclusions or alternatives are named, leaving the agent to infer usage context, which is insufficient given the presence of related job-management siblings.

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