cw_job

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

With no annotations, the description does real work: 'Read' establishes read-only semantics, and the enumerated return fields cover progress and terminal outcomes (result or error), which is the behavior an agent needs for a polling loop. It omits edge behavior such as an unknown/expired job id or how to detect completion and stop polling.

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?

Two sentences, zero filler. The identification of what is read comes first, followed by the polling instruction, so the actionable guidance is not buried.

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 one-parameter read tool with no output schema, describing the return contents inline is the right compensation, and the polling hint completes the async workflow. Minor remaining gap: no mention of terminal states or what to do if the job is gone.

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% and the single 'id' parameter is already documented as 'Job id, as returned by a slow tool', which the description essentially restates. No additional format, length, or sourcing guidance is added, so 3 is the appropriate baseline.

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?

"Read one background job by id" gives a specific verb and resource, and the colon-list (state, elapsed time, progress trail, result or error) tells the agent exactly what comes back. The singular 'one ... by id' implicitly separates it from the plural sibling cw_jobs, but no sibling is named outright.

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?

"Poll this after a slow tool returns a job id" is an explicit trigger condition tied to the async pattern, which is the main ambiguity for a job-inspection tool. It stops short of naming alternatives (cw_jobs, cw_job_abandon, cw_job_clear) or stating when not to poll.

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