shell_job_kill

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

With no annotations, the description carries the full burden. It usefully discloses that the whole process tree is killed (not just the parent), which is important destructive behavior. It does not state error behavior for an unknown/finished job_id, permissions required, or whether the kill is graceful or forced.

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?

One front-loaded sentence states the action and scope, followed by a compact args block. Nothing is wasted, though the args line largely restates the single parameter.

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?

For a single-parameter, no-output-schema tool, the description covers the essential action, scope, and where the id comes from. Missing details are minor (return value, error cases), so it is complete enough for correct invocation.

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 only schema detail is a title 'Job Id'. The description compensates by explaining the id's provenance ('Id returned by shell_start'), which is genuinely useful for obtaining the value. It adds meaning beyond the schema but not full syntax or validation details.

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 ('Kill') and resource ('a background job and its whole process tree'), with the scope of the kill made explicit. It doesn't explicitly differentiate itself from siblings like shell_job_wait or shell_job_output, but the destructive action is unambiguous.

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 note that job_id is 'Id returned by shell_start' implies the lifecycle context (start then kill), which is a form of usage guidance. However, there is no explicit when-to-use or when-not-to-use guidance against alternatives like shell_job_wait or shell_job_output.

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