mesh_layer_plan

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description goes beyond them with the key caveat that 'the result is a plan, not evidence that Gmsh created or validated the requested layers' and with the per-fit behavior (strict rejects inconsistent inputs; adjust_ratio preserves first height and count; adjust_first_height preserves count and ratio) — genuinely useful traits not present in structured fields.

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?

Dense and front-loaded: the lead sentence states purpose and scope, then parameters, then fit behavior, then the plan-vs-validation caveat. Every sentence carries information and nothing is redundant.

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?

With an output schema present, return values need not be described, and the description appropriately focuses on input constraints, fit-mode behavior, and the caveat that output is a plan. It is nearly complete, though it omits units and does not explicitly differentiate itself from the grading siblings.

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 carry the parameter burden, and it largely does: it names first_cell_height, cells, growth_ratio, thickness, and fit, and explains the preservation semantics of each fit value (including values not enumerated in the schema). It is missing units and the meaning of the 1–256 cell bound, so it is not fully compensating.

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+resource ('Plan one-sided geometric wall layers') with an explicit scope qualifier ('without modifying a model'), so an agent immediately knows this is a read-only planning/compute call rather than a model mutation. It hints at the downstream consumer (structured block extrusion) but does not directly name or contrast a sibling such as mesh_grading_calculate or mesh_grading_two_sided.

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 supplies a concrete precondition: 'Supply first_cell_height plus at least two of cells, successive-cell growth_ratio and total thickness', and explains when each fit mode applies (strict rejects, the adjust modes preserve different quantities). This is clear usage context, but it never names an alternative tool or states when NOT to use this one versus the mesh_grading siblings.

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