Undo Job

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

Description adds the constraint 'completed job' beyond annotations (destructiveHint, idempotentHint). But doesn't disclose what exactly gets destroyed (e.g., transcripts, model updates) or authorization needs. No contradiction with annotations.

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?

Single sentence, no wasted words, front-loaded with action. Excellent 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?

Minimal completeness: lacks details on scope of undo, reversibility, prerequisites, or consequences. For a destructive tool, more context is needed.

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% with 'Resource ID' for jobId. Description doesn't add meaning beyond that. Baseline 3 for full coverage.

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?

Description clearly states verb 'Undo' and resource 'results of a completed job', distinguishing it from job_kill (running jobs) and job_restart. However, 'undo' is vague; does it revert to pre-job state or just remove outputs? Title 'Undo Job' slightly misaligns with 'undo results'.

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?

No explicit guidance on when to use vs alternatives. Implies only for completed jobs but doesn't state exclusions (e.g., running jobs). Sibling tools like job_kill and job_restart_all_by_user are not mentioned.

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