check_convergence

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

Adds substantial behaviour beyond the annotations: relative cost (~3x a single run), an async contract (returns a job_id past ~20 s), and an objective success threshold (GCI <= 5%). It does not say whether artifacts are persisted on the case or how to retrieve the GCI/Richardson values, but the safety and timing profile is well covered.

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?

Three dense sentences: purpose first, then the decision rule, then cost and async behaviour. No filler and nothing redundant with the structured fields.

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 multi-solve, potentially long-running operation with no output schema, the description covers cost, the async job_id fallback and the pass criterion. It could say more about what is reported on success (GCI values, extrapolated result) and that job_status must be polled, but an agent has enough to invoke it correctly.

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 the description never mentions either parameter. case_id is inferable from context, but language (ja/en/zh, default ja) — which plausibly controls the output language of the report — is left entirely to the schema, so the description compensates for none of the coverage gap.

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?

States a concrete verb sequence and resource (solve on coarse/normal/fine meshes, estimate discretisation error via Roache's GCI and Richardson extrapolation), which is clearly distinct from siblings like run_simulation, validate_case or verify_case. An agent can tell what this tool produces without opening the schema.

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?

"For shapes without an analytic reference this is the third gate, mesh convergence (passes when GCI <= 5%)" gives a clear use condition and a pass criterion, implying it belongs after geometry/mesh checks. It stops short of naming the sibling gates or stating when to skip this (e.g. analytic reference available), so no explicit alternatives are offered.

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