Skip to main content
Glama
neozhehan

Figma Edit MCP

by neozhehan
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

Delete Nodes

node_delete
DestructiveIdempotent

Delete multiple Figma nodes in one batched call, with per-item validation and automatic retry for failed or skipped items to ensure complete removal.

Instructions

Delete one or more nodes in a single batched, per-item-validated call. No API undo. If the status is 'partial_success', treat it as an incomplete operation, report the failed and skipped items to the user, and retry every non-success item (both failed and skipped).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nodesYesArray of nodes to delete

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNo
statusNoOverall status of the batch operation
resultsNoDetailed deletion results (one row per input, in input order)
successNoWhether all deletions succeeded
failedCountNoNumber of failed deletions
skippedCountNoNumber of skipped deletions
requestedCountNoNumber of requested deletions
succeededCountNoNumber of succeeded deletions

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed17 schema fields changedv2.3.3
    • addedInput schema / properties / nodes / items / additionalProperties
      Added value: +false
    • changedInput schema / properties / nodes / items / properties / nodeName / description
      Previous value: -"Name of the node to modify"New value: +"The node's current exact name, passed back verbatim from `node_info`."
    • addedInput schema / properties / nodes / minItems
      Added value: +1
    • removedOutput schema / properties / deletedCount
      Removed value: -{
-  "description": "Number of deleted nodes",
-  "type": "number"
-}
    • addedOutput schema / properties / error
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "code": {
+      "description": "Stable machine-readable failure code (see the error playbook)",
+      "type": "string"
+    },
+    "details": {
+      "description": "Optional structured context (e.g. partialMutation, before-values)"
+    },
+    "message": {
+      "description": "Human/agent-readable message embedding its own recovery",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}
    • addedOutput schema / properties / failedCount
      Added value: +{
+  "description": "Number of failed deletions",
+  "type": "number"
+}
    • addedOutput schema / properties / requestedCount
      Added value: +{
+  "description": "Number of requested deletions",
+  "type": "number"
+}
    • changedOutput schema / properties / results / description
      Previous value: -"Detailed deletion results"New value: +"Detailed deletion results (one row per input, in input order)"
    • addedOutput schema / properties / results / items / additionalProperties
      Added value: +{}
    • addedOutput schema / properties / results / items / properties
      Added value: +{
+  "before": {
+    "description": "Q9/Q24: diagnostic evidence of the known pre-mutation state; not guaranteed to be a directly executable restoring-write input"
+  },
+  "error": {
+    "description": "Actionable reason, REQUIRED on any non-success row (Q25 contract key)",
+    "type": "string"
+  },
+  "nodeId": {
+    "description": "Identity of the target node (Q25 contract key)",
+    "type": "string"
+  },
+  "partialMutation": {
+    "description": "Q9/Q24: set when the item mutated before it failed",
+    "type": "boolean"
+  },
+  "status": {
+    "description": "Per-item outcome (Q25 contract key)",
+    "enum": [
+      "success",
+      "failed",
+      "skipped"
+    ],
+    "type": "string"
+  },
+  "success": {
+    "description": "Legacy per-row boolean; mirrors status === 'success'",
+    "type": "boolean"
+  },
+  "whatChanged": {
+    "description": "Q9/Q24: plain-language statement of what changed",
+    "type": "string"
+  }
+}
    • addedOutput schema / properties / results / items / required
      Added value: +[
+  "nodeId",
+  "status"
+]
    • addedOutput schema / properties / results / items / type
      Added value: +"object"
    • addedOutput schema / properties / skippedCount
      Added value: +{
+  "description": "Number of skipped deletions",
+  "type": "number"
+}
    • addedOutput schema / properties / status
      Added value: +{
+  "description": "Overall status of the batch operation",
+  "enum": [
+    "success",
+    "partial_success",
+    "failed"
+  ],
+  "type": "string"
+}
    • addedOutput schema / properties / succeededCount
      Added value: +{
+  "description": "Number of succeeded deletions",
+  "type": "number"
+}
    • changedOutput schema / properties / success / description
      Previous value: -"Whether the operation succeeded"New value: +"Whether all deletions succeeded"
    • removedOutput schema / required
      Removed value: -[
-  "success"
-]
  2. Changed1 schema field changedv2.3.2
    • changedOutput schema / additionalProperties
      Previous value: -falseNew value: +{}
  3. Changed1 schema field changedv2.3.0
    • addedInput schema / additionalProperties
      Added value: +false
  4. Addedv2.0.0

TDQS

A4.5/5.0
Behavior5/5

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

The description goes beyond annotations by disclosing 'No API undo,' per-item validation (which implies possible partial success), and specific retry semantics. These details complement the destructiveHint and idempotentHint annotations without contradiction, adding significant behavioral context.

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

Conciseness5/5

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

The description is three sentences, each purposeful: core function, warning about undo, and failure-handling instructions. It is front-loaded and extremely concise with no wasted words.

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?

With annotations covering idempotency and destructiveness, and an output schema presumably explaining return values, the description thoroughly covers batching, validation, and partial-success handling. It is complete for a delete operation with no significant gaps.

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

Parameters3/5

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

Schema coverage is 100% (nodeId and nodeName are well-described), so the baseline is 3. The description does not add parameter-specific syntax or format details, but the 'per-item-validated' phrasing hints at how the nodes array is processed, which is marginal added value over 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 clearly states 'Delete one or more nodes in a single batched, per-item-validated call,' which specifies the verb (delete), resource (nodes), and distinguishes the tool by its batched and per-item-validated nature. This is precise and leaves no ambiguity about what the tool does.

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?

It provides clear usage context: a batched deletion with no API undo, and explicitly instructs how to handle partial_success responses (report failed/skipped items and retry them). However, it does not name alternative tools or exclusion cases, though no direct sibling alternative for node deletion exists in the list.

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/neozhehan/figma-edit-mcp'

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