job_start

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

No annotations provided, so the description carries the full burden. It explains that the job runs in the background, returns a durable job_id for later checks, and how timeout policies work. It does not mention destructive behavior or authentication needs, but the described behavior is complete enough.

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. First sentence captures the main purpose, second provides actionable usage guidance. Every word earns its place.

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?

Given the high parameter count (9) and the presence of an output schema, the description covers the essential aspects. It mentions the durable job_id return and differentiates from sibling tools, providing enough context 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%, so the description must compensate. It explains six key parameters (expected_runtime_seconds, timeout_seconds, check_after_seconds, poll_interval_seconds, on_timeout, and implicitly command) with usage details. However, it omits cwd, env, and name, which could leave gaps for an agent.

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 clearly states it starts a durable background job with explicit execution timing policies. It distinguishes from sibling tools like job_cancel and job_status by focusing on the start action and timing choices.

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?

Explicitly advises to deliberately choose timing parameters and provides concrete guidance on when to use each on_timeout value (continue_background for long work, kill/return_partial for bounded synchronous work). This helps the agent select the right behavior.

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