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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses non-obvious behavior: no remeshing when preparing sections, the 1 GiB native-vs-preview fallback threshold, that cells never silently falls back to a preview, that a cutaway is not a volume cross-section, and that a pending operation_id may be returned instead of results. The one gap is that the preview fallback is only partly characterized (labelled preview 'when available'), leaving an agent unsure what happens when no preview exists.

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?

Purpose is front-loaded and nearly every clause carries operational meaning (thresholds, fallbacks, alternatives, async polling). It is, however, a dense run-on block of semicolon-chained facts that would scan better as short sentences grouped by intent (when to use / parameter rules / async results).

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?

Given a 4-parameter tool with an output schema and a hosted async viewer, the definition covers what an agent needs: correct input artifact, parameter selection rules, fallback semantics, what the browser shows and does not show, and the exact polling workflow. Return values are rightly left to the output schema except for the instruction to surface the full viewer_url rather than embedded HTML.

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 only 50% schema description coverage, the description carries the load well: surface_detail is fully explained (cells requires native topology and errors rather than degrading; preview selects lightweight display geometry whose triangles are not volume-cell faces; omission has a size-dependent rule), zone/patch_names are described as exact smaller-view selectors, and artifact_id is constrained to the job's CGNS mesh rather than CAD.

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 opens with a specific verb and resource ('Open the saved mesh in the Gradient Dynamics interactive 3D Y-up browser') and immediately enumerates the view's concrete capabilities (presets, cell edges, boundary colours, probes, 2D slices). It also distinguishes itself from siblings by naming view_mesh_section and assemble_mesh_viewer for saved planes.

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 states which artifact to pass ('this job's mesh_cgns, not CAD'), when to choose surface_detail=cells vs preview vs omission, when to use zone/patch_names to narrow the view, and explicitly routes plane requests to view_mesh_section/assemble_mesh_viewer. It also gives the async protocol: continue with get_operation at retry_after_seconds, never resubmit to poll.

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