run_simulation

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

Annotations only say it is a non-idempotent, non-destructive write; the description adds the genuinely useful behavior: a blocking wait of ~20 s with a fallback async path, the two return shapes, and the domain rule that electrostatics and DC/Joule always use the built-in FEM. It does not cover failure behavior, cost/duration, or what happens if a job is already running, so it is strong but not exhaustive.

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?

Front-loaded with the action and the wait behavior, then the follow-up, then mode semantics — good information ordering in only three sentences. Some density and shorthand ("returns results and gates") slightly hurt scannability, but nothing is redundant.

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 job-launching tool with no output schema and no annotations on return values, the description covers the essentials: blocking behavior, the two possible outcomes, and the next tool to call. The only real omission is the unexplained 'language' parameter and any note on error or concurrent-job handling.

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 carry the parameter burden. It does explain the important 'mode' enum well (preview vs final, and the built-in-FEM override for certain physics), but 'case_id' and especially 'language' (ja/en/zh, default ja) are never mentioned, leaving one of three parameters with no semantics anywhere.

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?

"Start the solver as a background job" gives a specific verb and resource, and the description names the immediate follow-up tool (job_status) plus the solver variants (built-in vs CalculiX/OpenFOAM). It does not explicitly distinguish this from run_sweep or instant_estimate, which are the closest siblings, so it stops just short of a 5.

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 clearly states the branch condition: if the job finishes within ~20 s you get results, otherwise you get a job_id and should call job_status. Mode semantics are also given (preview = built-in, final = CalculiX/OpenFOAM when the template offers it), which tells the agent how to choose. Missing is guidance on when to prefer instant_estimate or run_sweep instead of launching a solver.

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