fem_mesh_refinement

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

With no annotations, the description bears the full burden. It discloses that the operation adds to an existing mesh and that char_length must be smaller than the global setting to actually refine, which is a useful behavioral condition. However, it does not state whether the mesh is modified in place or a new handle is returned, nor any permission or reversibility details, leaving major behavioral gaps for a mutation tool.

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?

The description is front-loaded with the purpose, then a compact parameter glossary. Every sentence contributes; there is no repetition or filler.

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 FEM mesh-modification tool with no annotations and no output schema, the definition covers the core action and most parameters, but it omits the optional 'name' parameter, mutation/return semantics, and how this tool fits between fem_mesh and fem_run. It is minimally adequate but not fully 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. It explains mesh (handle), refs (list of dicts with handle and face/edge/tag), and char_length (units in mm and a constraint relative to global mesh), covering three of four parameters. The optional 'name' parameter is not described.

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 states a specific verb ('Add'), resource ('local mesh-refinement region'), and target ('existing FEM mesh'), which clearly distinguishes it from global mesh generation (fem_mesh) and downstream solve tools. It is not a tautology and an agent can identify the action 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?

It implies usage ('on an existing FEM mesh') and gives a condition for effect ('char_length should be smaller than the global mesh setting to actually refine'), but it does not explicitly say when to use this versus fem_mesh or other mesh tools, nor any exclusions. Usage is only implied.

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