Skip to main content
Glama
danielproxd2

MCP_CAD

by danielproxd2

verify_against_spec

Verifies built-part size against drawing specifications by measuring the bounding box and comparing to transcribed dimensions within tolerance, catching the common failure of correct shape but incorrect size.

Instructions

Verifica el TAMAÑO de la pieza construida contra el spec del dibujo.

ADVISORY — el ÚNICO chequeo independiente de verdad-de-tierra en el loop: mide el sólido construido (get_bounding_box) y lo compara numéricamente, con tolerancia, contra las dimensiones que transcribiste del dibujo. Convierte el "se ve bien" visual sin dimensiones en una aserción dura de envolvente — atrapa la clase de error más común e invisible: forma correcta, tamaño equivocado.

Args: expected_size_mm: tres extensiones esperadas [a, b, c] en mm, en CUALQUIER orden (con match_by="sorted"). tolerance_mm: banda mínima por eje (default 0.5mm). tolerance_pct: banda relativa por eje; se usa max(mm, pct). Default 1%. expected_volume_mm3: opcional — chequeo de volumen SOLO de orden de magnitud (nunca cambia el veredicto; evita falsos positivos por chaflanes/redondeos legítimos). Útil para detectar errores de unidades. match_by: "sorted" (default, robusto a orientación) o "positional".

Returns dict: {ok, verdict PASS/FAIL, per_axis (deltas), measured_size_mm, volume?, caveats[], message, bbox}. LEE los caveats: la caja NO ve features en ubicación incorrecta del mismo tamaño, topología incorrecta, ni errores que conservan el envolvente. Es un oráculo entre varios, no la corrección total.

[en: Verify built-part SIZE against the drawing spec. Advisory — the first independent ground-truth check in the loop: measures the solid via get_bounding_box and asserts it against transcribed dims within tolerance, turning a dimensionless visual "match" into a hard envelope assertion. Catches the most common, most invisible failure: right shape, wrong size. Optional volume check is order-of-magnitude only (never flips the verdict). Read the caveats — bbox cannot see wrong-location, wrong-topology, or envelope-preserving errors.]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
match_byNosorted
tolerance_mmNo
tolerance_pctNo
expected_size_mmYes
expected_volume_mm3No
Behavior5/5

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

No annotations are provided, so the description carries the full burden. It details the internals: uses get_bounding_box, numeric comparison with tolerance, optional volume check (order-of-magnitude only, never flips verdict), and the return structure. It also discloses limitations and caveats.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is detailed but well-structured with Spanish and English versions. It is front-loaded with the core purpose and then provides arg explanations. A minor concession for length, but every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (5 params, no output schema), the description covers necessary behavioral details, output structure, and caveats. It also references related tools (get_bounding_box). It is complete for an agent to understand when and how to use the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description thoroughly explains each parameter: expected_size_mm (three extensions in any order), tolerance_mm (minimum band), tolerance_pct (relative, uses max), expected_volume_mm3 (optional, order-of-magnitude), match_by (sorted vs positional). It adds significant meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool verifies built-part size against the drawing spec, contrasting with visual checks. It clearly identifies the resource (built part size) and the action (verify). It distinguishes itself from other verification tools by being an independent ground-truth check.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use this tool (as the first independent ground-truth check) and when not to rely solely (caveats: cannot see wrong location, topology, envelope-preserving errors). It provides context on the kind of errors it catches, but does not explicitly name alternative tools for other types of checks.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/danielproxd2/solidworks-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server