probe_results

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

Annotations already declare a safe, idempotent read, yet the description adds substantial behavior beyond that: quadratic interpolation on tet10 elements, outside-part handling (inside=false plus nearest node value), a 500-point cap per call, exact solver fluxes on inlets/outlets versus nodal estimates elsewhere, and sign conventions for flow. These are details an agent could not infer from the schema or annotations.

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 three selectors, then quantities, then semantics and caveats. Dense but nearly every clause carries information; the long quantity enumeration and unit strings are the bulkiest part but are genuinely needed to know what comes back.

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 an 8-parameter, no-output-schema tool, it covers selector formats, output semantics per selector, sign conventions, limits, and unsupported case types. Missing only run_id behavior (does it default to the latest run?) and the language parameter, which are minor gaps rather than blockers.

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?

With zero schema description coverage, the description carries the burden and mostly succeeds: points format, line shape with from/to/n and its min/max output, faces as face keys with area-weighted statistics, step as a one-based converged nonlinear frame (omitted = last), and mode for modal shapes. run_id and language are left unexplained, which keeps it short of a 5.

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 specific verb and resource: reads result values at user-specified points, lines, or faces, and enumerates the quantities returned per physics type. An agent can tell exactly what it produces. It does not, however, contrast itself with get_results or export_results, so the boundary with siblings remains inferred.

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?

Use is implied by 'where you ask' and by the per-selector explanations, and it gives an explicit exclusion ('Not available for 2D template grids or snappyHexMesh runs'). But there is no guidance on when to prefer this over get_results, export_results, or instant_estimate, which is the main ambiguity for an agent.

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