shell_job

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

With no annotations, the description carries the burden and usefully discloses that output/wait can block up to wait_ms and that offset supports incremental streaming via next_offset. It does not discuss permissions, side effects of kill/remove, or default behavior beyond what the schema already states, but the key blocking and streaming behaviors are surfaced.

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?

Three compact sentences: purpose and action list first, then blocking behavior, then offset streaming. Every sentence adds useful information with no repetition or filler.

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 an eight-parameter control tool with no output schema, the description covers the core mental model and the critical streaming protocol. It leaves some return-value and destructive-action context to the schema, but it is complete enough to invoke the tool correctly.

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 coverage is 100%, so the baseline is 3, but the description adds meaningful semantics for offset and wait_ms by explaining how next_offset enables streaming without re-reading. It does not explain every parameter, but it improves the most important ones beyond the schema.

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 states a specific verb and resource: 'Inspect and control background jobs.' It enumerates all seven actions, making clear that this is the job-management tool rather than an execution tool like shell_exec or shell_exec_async.

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?

It gives clear context for using output and wait, including that blocking up to wait_ms replaces a polling loop and that next_offset should be reused as offset. It does not explicitly name alternatives such as shell_exec_async or state when not to use this tool, so it stops short of full routing guidance.

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