job_start

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the bar is lower, yet the description still adds real behavioral content: the source state (queued), the fields written (worker, started_at), and that a repeat call errors rather than no-ops. It stops short of saying what happens if the job is not queued (error vs. overwrite) or what the response contains.

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, no filler, with the transition front-loaded. The telegraphic 'queued -> running' fragment is efficient but drops the subject, which costs a little immediate readability for a first-time reader.

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?

An output schema exists and annotations cover the safety profile, so much of the burden is lifted. Still missing for a state-mutating tool in a dense job-tool cluster: the failure mode for a non-queued job, and any pointer to which sibling handles the adjacent steps.

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 100% — both job_id (with format example and provenance from job_enqueue/job_list) and worker (with a concrete id example) are fully documented in the schema. The description adds nothing about parameters, so the baseline 3 applies.

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 the state transition ('queued -> running') and what gets recorded, but it omits an explicit verb+object framing and never distinguishes this from the many adjacent job tools (job_assign, job_next, job_attach, job_restatus). An agent reading the name plus this line can infer 'start a queued job', but the sibling boundary is left entirely unstated.

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?

'A second call is a conflict' is a genuine when-not constraint that steers the agent away from repeated invocation. However, there is no positive guidance on when to pick job_start over job_assign or job_next, and no stated precondition that the job must still be queued for the call to succeed.

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