Skip to main content
Glama
tathagat22

Plumb (plumb-mcp)

by tathagat22

Plumb · review

plumb_review
Read-onlyIdempotent

Self-critiques Figma designs against authored intent and design rubrics, scoring structure, design, and optional vision grade, then coaches iterative refinements to meet quality targets.

Instructions

Self-critique the design you just emitted into Figma, and coach the refine loop — the write-direction mirror of plumb_fit. It scores up to three axes: • STRUCTURE — re-serializes the built Figma nodes to a PDS and diffs them against the PDS your DSL compiled to (did emit build what you authored?). Uses the same verify engine as plumb_verify/plumb_fit. The two docs are joined by ids = EmitResult.ids (authored el → Figma node id) — pass it or the diff can't line up. • DESIGN — a deterministic rubric over hierarchy, spacing rhythm, contrast (WCAG AA), alignment, type-scale, and professional-vs-templated polish. Failing contrast is an error and blocks done. • DIRECTOR (optional, director: {score, verdict?, issues?}) — a vision creative-director grade of the rendered screenshot: visual balance, focal flow, image composition/crop, optical spacing, and the "designed vs generated" gestalt a deterministic pass over the PDS can't see. There is NO server-side vision call and NO API key needed here — YOU (the calling agent) already have vision, so YOU grade the screenshot yourself and pass your verdict in. The loop: call plumb_screenshot on the emitted rootId, look at the PNG, grade it as a demanding creative director (any response with no director input echoes the exact grading criteria + output shape at the end of its instruction), then call plumb_review again passing director: { score, verdict, issues }. With the director present, weights reshuffle to structure 0.4 / design 0.3 / director 0.3 and a director error-severity issue blocks done too, so the bar is harder (and more honest) to clear. Returns: score (0–100 blended), done, bar, topFixes (error-first across all active axes, director fixes tagged [director/<dim>]), instruction, dimensions[] (per-rubric-dimension sub-scores), directorScore/directorVerdict when graded, plus the raw structural deltas + coverage. Provide the authored PDS inline via authored, or a path to it via authoredPath (the JSON plumb_apply writes). Point id/name/url at the emitted root (EmitResult.rootId). Canonical loop: plumb_design → repeat[ plumb_screenshot (rootId) → grade it yourself → plumb_review(..., director: {score, issues}) → if !done, apply topFixes and plumb_design(mode:"sync") ] until done or an iteration cap. If done=false, apply topFixes, re-apply the DSL (mode:"sync" keeps plumbKey), and call plumb_review again — the score should climb.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoEmitted root node id (EmitResult.rootId).
idsNoEmitResult.ids — authored el → Figma node id. The join key for the structural diff.
urlNoPaste a full Figma URL — fileKey and node-id are auto-extracted.
nameNoScreen name (plugin path).
briefNoOptional design intent (type scale, fonts, spacing grid) to grade against.
depthNoPDS depth to re-serialize. Default 12.
acceptNoBlended score at which to stop. Default 90.
fileKeyNoFile key (REST path).
authoredNoThe authored PdsDocument (what the DSL compiled to). Inline alternative to authoredPath.
directorNoYOUR OWN vision grade of the rendered screenshot — no server-side model call, no API key. Look at the PNG from plumb_screenshot, grade it yourself as a demanding creative director (see directorGuidance in a no-director response for the exact criteria), and pass { score, verdict?, issues? } here. When present, reweights the blend to structure 0.4 / design 0.3 / director 0.3 and a director error blocks `done`.
iterationNoWhich refine pass this is (1, 2, 3…). Informational — sharpens the coaching.
tolerancesNoOverride default structural thresholds.
authoredPathNoPath to a JSON file holding the authored PdsDocument (written by plumb_apply).
Behavior5/5

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

Annotations declare readOnlyHint=true and idempotentHint=true. The description adds context that the tool uses the same verify engine as plumb_verify/plumb_fit, that there is no server-side vision call for the director, and describes the return values. 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.

Conciseness2/5

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

The description is overly long (over 600 words) and lacks structured formatting like bullet points. While detailed, it is not concise and could be more organized for quick parsing.

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 (13 parameters, nested objects, no output schema), the description is extremely comprehensive, covering the full workflow, axes, return fields, and iteration logic. It leaves no gaps.

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 coverage is 100% and the description adds meaning to each parameter beyond the schema, explaining their roles (e.g., ids as join key, director as vision grade) and interactions (e.g., director presence reshuffles weights).

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 clearly states that the tool self-critiques the emitted Figma design and coaches the refine loop. It distinguishes itself as the 'write-direction mirror of plumb_fit' and specifies three axes (STRUCTURE, DESIGN, DIRECTOR), providing a specific verb and resource.

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?

The description provides explicit when-to-use and how-to-use guidance, including the canonical loop with plumb_screenshot and plumb_design. It also explains when not to use alternatives and includes prerequisites like passing EmitResult.ids.

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/tathagat22/plumb-mcp'

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