start_job

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

Beyond the annotations, the description discloses important lifecycle and concurrency behavior: session-local job IDs, retention of the latest 64 jobs, at most four active jobs and one native solver, survival of artifacts and sweep summaries across restarts, and cancellation when the server closes.

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?

The description is four sentences, front-loads the core action, and every sentence contributes operational information or constraints. There is no redundant restatement of the tool name.

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 complex background-job tool with no output schema, the description covers session requirements, concurrency limits, retention, restart behavior, and cancellation well. It does not explicitly state what start_job returns, such as a job ID, but that is implied by the instruction to poll job_status.

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 for parameter meaning. It only says 'run or sweep,' vaguely matching the request oneOf variants, but it does not explain operation, path, timeout, component, parameter, values, or other request fields.

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: 'Start a background run or sweep.' It also names related tools job_status and cancel_job, but it does not explicitly distinguish start_job from the synchronous-sounding siblings run_schematic and parameter_sweep.

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 operational context: start a background operation, poll with job_status, and stop via cancel_job. It also states the prerequisite of a persistent MCP session, though it does not explicitly say when to choose start_job over run_schematic or parameter_sweep.

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