job_details

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

Annotations already declare readOnly/idempotent/non-destructive, so the description focuses on what it returns and adds genuine behavioral detail beyond them: which instance is used for exit status/timing/stderr ('canonical (or a failed) instance') and that stderr_tail is measured in characters. That selection logic is not derivable from the 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?

A single dense sentence front-loads the core return (instances and states) before the conditional extension, with no filler. The sentence is long and the parenthetical nesting costs a little readability, but essentially every clause carries information.

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?

With an output schema present, the description needn't enumerate return fields, and it instead covers the conditional behavior that shapes the response and the cross-tool dependency for job_name. The main remaining gap is the absence of guidance on choosing among sibling tools.

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%, so the description must compensate, and it does for two of three parameters: job_name is explained as coming from batch_jobs and as gating the extended output, and stderr_tail is clarified as a character count. Only job_id is left unstated, which is acceptable given the shared naming convention.

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?

States a specific resource and payload: a single job/workunit with its instances and instance states, plus optional per-instance detail when job_name is supplied. It also names the sibling (batch_jobs) that supplies job_name, which helps separate it from batch_status and batch_jobs, though it does not explicitly contrast its role.

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 intended flow ('if `job_name` is given (from batch_jobs)') and the consequence of omitting it, but never states when to prefer batch_status or batch_jobs instead, nor any prerequisites. Usage is inferable rather than explicit.

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