start_solver

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

With no annotations, the description carries the full burden, and it does disclose the key async trait: it returns immediately and results must be polled. It does not say what happens if the CAD job is not complete, what the immediate return contains, or whether a prior solver run is overwritten.

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 short sentences, zero filler, and the async contract plus the follow-up tool are front-loaded so an agent knows the pattern immediately.

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 simple fire-and-poll tool the essential flow is conveyed, but with no output schema, no annotations, and entirely undocumented parameters, the description should say more about the immediate return value and failure modes before it is fully callable.

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 0% across three parameters, so the description must compensate and does not: cores (default 4), model_filename (default mba_preliminary.cfx), and job_id are never explained. Only a loose hint that job_id refers to a CAD job exists.

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 gives a specific verb+resource: starting the FEKO solver inside an already-completed CAD job. It differentiates the tool from siblings by naming get_job_status as the follow-up rather than doing the work itself, though it does not contrast itself with run_cad_script or run_post_script.

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?

"in a completed CAD job" states the precondition for calling it, and "then poll get_job_status" names the next tool explicitly. There is no explicit when-not guidance, but the sequencing is unambiguous.

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