run_job

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

With no annotations, the description carries the burden of disclosure. It meaningfully explains that MCP clients receive a Task handle immediately while older clients block, and that client_request_id enables retry safety. This is valuable behavioral context, though it does not cover all side effects or failure modes.

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 three concise sentences, front-loaded with the core purpose ('Run one durable job'), followed by two sentences that add essential behavioral and retry context. No word is wasted.

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?

While an output schema exists (so return values are covered), the tool has 11 parameters and no parameter descriptions. The description does not explain the distinction from submit_job, nor does it cover key parameters or usage prerequisites, making it incomplete for correct and confident 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% and there are 11 parameters, but the description only explains the client_request_id parameter. Other important parameters like cwd, env, backend, slurm_options, and timeout_seconds are undocumented, leaving the agent under-informed for invocation.

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 'Run one durable job,' which is a specific verb+resource and adds the 'durable' qualifier. However, it does not distinguish run_job from the sibling submit_job, so it lacks sibling differentiation.

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?

The description provides no guidance on when to use run_job versus submit_job or other siblings. It only notes protocol differences for MCP vs older clients, but no explicit usage context or exclusions.

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