mesh_import

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

With no annotations, the description carries the full burden and does so well: it explains the dimension-to-entity mapping (highest dim → elements, next lower → conditions), that a 'domain' sub model part is always added, which cell types are accepted, that cubic and higher-Lagrange cells are rejected, and that 15-node wedges/13-node pyramids are refused on export. It omits what happens on output collisions (overwrite defaulting to false) and whether the output file is otherwise modified, leaving a small gap.

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 in the first sentence and the remainder is dense, non-repetitive technical detail rather than padding. It is on the long side and mixes conversion rules, supported-cell enumeration and parameter guidance into one block, which slightly dilutes scannability.

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 7-parameter format-conversion tool with an output schema (so return values need no explanation), the description gives enough to call it correctly: source/output roles, format override, and Kratos type selection. The undocumented property_id and overwrite behavior are the remaining omissions keeping it from complete.

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 compensate, and it does explain element_name, condition_name and file_format (including their defaults and intent). However property_id (default 1) and overwrite are never mentioned, so two of seven parameters remain semantically opaque.

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 precise verb+resource+scope: converting a foreign mesh format (gmsh, VTK, MED, Abaqus, Nastran, XDMF, anything meshio reads) into a Kratos .mdpa. It also names the reverse sibling (mesh_export linearize_unsupported), so an agent can distinguish it from mesh_export and mesh_generate_gmsh without opening any 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?

The opening sentence establishes when to reach for this tool (importing an existing mesh from another solver/format) and the closing notes when file_format is needed (ambiguous extensions), plus the element_name guidance for structural vs thermal/fluid cases. There is no explicit statement of when NOT to use it or a fuller contrast against mesh_generate_gmsh, so it stops short of a 5.

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