job_cancel

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

No annotations exist, so the description carries the full burden; it does disclose the key behavioral trait that the OS process group is terminated, which tells the agent this is a forceful, destructive action. It omits permissions/auth requirements, what happens to an already-finished job, whether termination is graceful, and the override relationship between the two parameters.

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 front-loaded sentence with the primary case first and the variant parenthesized; every clause carries information and nothing is padded.

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 return shape is covered by the output schema, and the core destructive behavior is named. But for a destructive, unannotated mutation, the description should still resolve the job_id-null vs cancel_all precedence and say something about jobs that are not currently running.

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. It adds real meaning for cancel_all ('all active jobs'), which the bare boolean/default does not convey, but job_id gets no explanation at all despite being nullable with a null default, leaving the mutual-exclusion/precedence question unanswered.

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 verb ('Cancel') on a specific resource ('a running job'), plus the scope variant for all jobs. The destructive action is unambiguous and clearly distinct from siblings like job_start and job_status.

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 condition (a job must be running, use cancel_all=True for all active jobs), but it never states what to do when neither job_id nor cancel_all is supplied, nor does it name the alternative tool to inspect state before cancelling. Usage is inferable rather than spelled out.

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