Skip to main content
Glama

run_feature_plan

Approve and execute the full FeaturePlan build in one pass, running all mutating steps as a single batch and verifying the result once at the end.

Instructions

Construye un FeaturePlan compilado en UNA sola pasada (compila una vez, construye una vez).

Flujo recomendado para dibujos/PDF:

  1. record_drawing_spec → fija la lectura.

  2. compile_feature_plan_from_drawing_spec → obtén el plan y MUÉSTRASELO al diseñador (pasos, dimensiones, advertencias).

  3. run_feature_plan(feature_plan_id) → ESTA llamada (aprobada en el cliente MCP) es la aprobación humana del build completo; ejecuta todos los pasos que mutan el modelo dentro de UN solo lote (redibujo/reconstrucción diferidos a una sola reconstrucción al final).

  4. revisa el verify_build_report devuelto + el render final.

[en: Build a compiled FeaturePlan in ONE pass. Show the plan to the designer after compiling; calling this tool (approved in the MCP client) is the single human-in-the-loop approval of the whole build. Mutating steps run inside one batch scope; verification runs once at the end.]

Compuerta de confianza: un plan marcado para "partial_or_handback" NO se construye solo — pasa override_low_confidence=True para forzarlo tras revisar las advertencias. Un plan con dimensiones sin resolver () se rechaza siempre: nunca se inventa una cota.

Compuerta de features internas: si el spec registró barrenos/ranuras punteadas que el plan NO modela (unmodeled_internal_features), se bloquea — pasa override_unmodeled_internal=True para construir sin ellas (flag independiente de override_low_confidence: forzar una no desactiva la otra).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
feature_plan_idYes
override_low_confidenceNo
override_unmodeled_internalNo
Behavior5/5

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

Despite no annotations, the description reveals key behaviors: it is the human-in-the-loop approval, executes all mutating steps in one batch with deferred rebuild, runs verification once at end, and enforces gates for low confidence and unmodeled internal features with separate overrides. No contradictions.

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?

Description is dense but well-structured: purpose, workflow (both in Spanish and English), then two gate paragraphs. Every sentence adds value, no fluff. Could be slightly more streamlined, but effective.

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

Completeness4/5

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

Given 3 parameters, no schema description, no output schema, the description covers usage, gates, and return (verify_build_report). Missing a bit of detail on the exact return structure, but mentions it briefly. Complex tool with good coverage.

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

Parameters4/5

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

Schema description coverage is 0%, but the description explains all three parameters in context: feature_plan_id (implied), override_low_confidence (force partial/handback plans), override_unmodeled_internal (build without unmodeled internal features). It also clarifies they are independent flags. However, no dedicated parameter descriptions, so slightly below perfect.

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?

Description clearly states 'Build a compiled FeaturePlan in ONE pass' and specifies it is the approval step for the whole build. It distinguishes from siblings like compile_feature_plan_from_drawing_spec and verify_build_report by providing a workflow (step 3).

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

Usage Guidelines5/5

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

Explicitly recommends a 4-step workflow with context for when to call this tool (after plan approval). Also explains when not to use: unresolved dimensions, partial_or_handback without override, unmodeled internal features without override. Provides clear alternatives for those cases.

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/MCP_CAD'

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