retry_artifact_collection

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

With no annotations provided, the description bears full responsibility for behavioral disclosure. It discloses that it does not rerun the compute job (a negative constraint), but it does not explain what restarting artifact retrieval actually entails—whether it deletes previous artifacts, requires specific permissions, has side effects, or returns any result. The description gives only a minimal behavioral trait without adequate transparency.

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, succinct sentence that front-loads the core action and the critical exclusion. Every word is purposeful, with no fluff or repetition. It is an excellent model of 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?

The tool has only one parameter and no output schema or annotations, so the description should provide enough context for safe and correct invocation. However, it lacks explanation of what 'exhausted artifact retrieval' means, what conditions warrant retrying, what the expected outcome is, or any potential failure modes. The description is too sparse to be complete for an agent that must decide when and how to use it.

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 has 0% description coverage, so the description must compensate for parameter documentation. The only parameter, job_id, is not mentioned in the description at all. While the name is self-explanatory, the description does not clarify whether job_id refers to the compute job ID or the artifact retrieval attempt ID, nor does it explain the expected format or usage. The description adds no value beyond the schema, leaving the parameter semantics poorly defined.

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 clearly states the action: 'Restart exhausted artifact retrieval' and distinguishes it from 'never rerun the compute job.' The verb 'restart' and resource 'artifact retrieval' are specific, and the exclusion of compute jobs differentiates it from potential sibling tools like submit_job or retry compute operations. It is not a tautology and provides a clear purpose.

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 the usage scenario: when artifact retrieval is exhausted, this tool should be used instead of rerunning the compute job. However, it does not explicitly mention alternatives such as fetch_artifact or list_artifacts, nor does it provide conditions for when not to use the tool beyond the compute job exclusion. The guidance is implicit rather than explicit, so it meets the 'implied usage' level.

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