Engrave Text

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

Discloses that the host solid is 'consumed/hidden and replaced by the returned handle', a mutation that matters to callers. Also documents the RuntimeError when no font is found, the macOS auto-probe fallback order, and that volume is less for engrave and greater for emboss. readOnlyHint=false already signals mutation, so this is additive context, not a contradiction.

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-loads the core purpose, then a single process sentence, then a tight parameter-by-parameter breakdown, then the return contract. Each parameter line carries distinct semantic weight with no filler; at roughly 250 words for a nine-parameter tool it is dense but appropriately sized.

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?

Complete for a high-complexity tool: 9 params, 0% schema coverage, no enums, and no output schema — yet the description supplies the return shape, volume semantics, error conditions, preconditions, units, and defaults. Nothing an agent needs to invoke it correctly is missing.

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 coverage is 0%, but the description documents all nine parameters with units (mm), defaults, allowed values, constraints (non-empty text, planar face), and failure modes. It even clarifies ambiguous schema types like position ([u, v] offset from centroid) and nullable font (auto-probe behavior). Fully compensates for the bare schema.

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?

Opens with a specific verb-plus-resource statement — 'Engrave (cut) or emboss (add) extruded text onto a planar face of a solid' — and clarifies the text is booleaned into the host. This distinguishes it from every sibling in the list, none of which perform face text marking. Goes well beyond the title by naming both modes and the geometric target.

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?

Gives concrete preconditions: the face must be planar and passed as a stable f_* tag from list_faces/query_faces, explicitly naming sibling tools that feed it. Explains when to choose mode='engrave' versus 'emboss' in terms of material removal versus addition. It does not name explicit alternative tools or when-not-to-use conditions, though no close sibling for text marking exists.

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