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

With no annotations supplied, the description carries the full burden and does disclose meaningful traits: it will not overwrite the input, mesh conversion is restricted to .FCStd or other mesh formats, and deflection values trade off fineness against facet count. It omits whether an existing out_path is overwritten and any permission requirements.

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 format-selection rule is front-loaded in the first sentence, followed by a compact list of outputs and the two mesh knobs. Every sentence carries information, though the flow is a bit cramped with several short fragments.

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 5-parameter export tool with no annotations, the description covers format routing, filtering, mesh quality and the key non-destructive constraint. An output schema exists so return values need not be explained; the lingering gap is the meaning of the required `path` parameter.

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%, so the description must compensate, and it does for most parameters: out_path's extension picks the format, objects matches Name or Label, and both deflection params are given meaning, units and a concrete direction of effect. Only `path` (the input model) is left unexplained.

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 and resource ('Converte um modelo') and enumerates the target formats selected by out_path's extension, so the agent knows exactly what the tool produces. It does not explicitly contrast itself with the sibling doc_export_2d, leaving the 2D-vs-3D split to inference from names.

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?

Usage is only implied: the agent can infer that mesh output cannot target .step/.iges/.brep and that omitting `objects` exports everything. There is no explicit when-to-use statement or reference to an alternative sibling such as doc_export_2d for 2D output.

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

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

With no annotations, the description carries the full burden and delivers: the input must be a solid or document and meshes are rejected, `offset` is silently ignored under projection, orientation is never mirrored (with the axis-to-view mapping), and output units are mm. It even describes what `wires` counts in the result, far beyond what structured fields provide.

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-loaded with the core action, then mode semantics, then constraints, then return meaning. Dense but every sentence carries new 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?

An output schema exists so return values needn't be spelled out, yet the description supplies mode rules, axis conventions, input constraints and the meaning of `wires`. Only the file-path and object-selection parameters remain unaddressed, which is a minor gap for an otherwise complete definition.

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 thoroughly explains mode, axis (z=top, y=frontal, x=right side) and offset, but leaves path, out_path and especially objects completely undefined in both schema and description.

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 specific verb and resource (generates .svg/.dxf in mm from a solid) and then distinguishes its two operating modes with concrete behavior, so an agent can identify it instantly without opening the schema. The '2D from solid' framing also implicitly separates it from the generic doc_export sibling.

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 explicit mode-selection guidance ('para laser, use este' for section; projection as preview/drawing), which is the main decision an agent must make. It does not, however, compare itself against the sibling doc_export or state when NOT to use this tool.

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

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the 100-object cap with `objects_total`, that units are always mm, the accepted file formats, and that `checks.watertight` is the FDM-printability decision. It never explicitly states this is a non-mutating read, which is the one gap given zero annotation coverage.

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?

Every sentence earns its place: purpose first, then accepted inputs, then return contract, then the downstream consumer of the object names. Dense but zero 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?

An output schema exists, so return values need not be documented — yet the description still maps the key return fields (`mesh`, `objects_total`, `checks.watertight`) and their significance, making it more than sufficient for correct invocation.

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% and the single `path` param is undocumented in the schema, but the description compensates by enumerating accepted formats (.FCStd, .step/.stp, .iges/.igs, .brep, .stl/.obj/.3mf/.ply) and stating that units are mm — directly useful semantics for supplying a valid path.

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 specific verb+resource (opens a model and returns dimensions, volume, validity, watertightness) and clearly distinguishes itself from the export siblings by noting that its name/label output feeds doc_export and doc_export_2d's `objects` parameter. An agent immediately knows this is the inspection step vs. the export step.

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?

Cross-references the alternatives explicitly: the returned `name`/`label` values are usable in doc_export and doc_export_2d, which implies inspect-first workflow. It does not spell out an explicit 'do not use this to modify' exclusion, so it falls just 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.

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

With no annotations, the description carries the behavioral burden, and it does disclose useful behavior beyond a plain version string: it reports which resolution rule matched (env, PATH, known path, flatpak, snap). The read-only, non-destructive nature is self-evident from the diagnostic framing, but it is never stated explicitly.

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?

Two short lines: the first states what is reported, the second front-loads the diagnostic use case and the resolution rules. No filler, and the most actionable instruction is placed immediately.

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?

An output schema exists, so the description need not describe return values, and with zero parameters there is no argument documentation burden. Purpose, usage trigger, and the shape of the diagnostic result are all covered for a simple zero-arg probe.

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?

The tool takes zero parameters, so the baseline is 4; there are no argument semantics for the description to clarify. Schema coverage is trivially 100%.

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?

Names a specific subject (FreeCAD version), an additional resource (embedded Python version), and the resolved command the server is using. It is unmistakably a diagnostic/inspection tool and none of the siblings (doc_inspect, doc_export, doc_export_2d, part_run_script) overlap with it.

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 an explicit usage trigger: 'First thing to call when something doesn't work'. That is a clear when-to-use directive, though it does not enumerate when-not-to-use or name any alternative (there is no comparable sibling anyway).

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

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: it documents the pre-populated namespace (doc, OUT_DIR, FreeCAD/App, Part, imports required for Mesh/Sketcher/PartDesign), the return payload (stdout, files, objects), the failure shape ({error} with traceback and stdout), the timeout range and default, and a security caveat that the script runs with user permissions and is not isolated by MCP_FREECAD_ALLOWED_PATHS.

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-loaded with the core purpose, and every sentence adds operational value (namespace, output, errors, timeout, security). It is dense and parenthetical-heavy, but there is no filler; only minor tightening is possible.

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 high-complexity arbitrary-code-execution tool with 3 params at 0% schema coverage, the description supplies invocation environment, output handling, error contract, timeout bounds and the critical sandboxing caveat. An output schema exists, yet the extra return-format detail reinforces rather than pads.

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 for all three parameters: `script` (what is pre-injected, what must be imported), `out_dir` (exposed as OUT_DIR, output files land there), and `timeout_s` (valid 5–900, defaults to MCP_FREECAD_TIMEOUT_S or 120). Nothing is left undocumented.

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 specific verb+resource ('Roda um script Python no FreeCAD headless') and immediately frames its niche against the sibling set ('a válvula de escape da API completa', covering what other tools don't: threads, parametric enclosures, game pieces). An agent can tell this apart from doc_inspect/doc_export 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?

Gives clear positive selection criteria — use it for geometry the other tools don't cover, with concrete examples (roscas, gabinetes paramétricos, peças de jogo). No explicit when-not-to-use or named alternative is given, 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.