Skip to main content
Glama
Figma Comments MCP

Figma Comments MCP

by RussGallaway

figma_delete_comment

Destructive

Permanently delete a specified Figma comment by ID as its author, with explicit authorization. Confirms the deleted target separately from replies that may also be removed.

Instructions

DESTRUCTIVE WRITE: permanently delete the explicit comment ID as its author. Deleting a root may also remove its replies. Returns confirmed target deletion separately from inferred affected replies. Requires explicit user authorization.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "file": "<file>",
      "commentId": "<commentId>"
    },
    "name": "figma_delete_comment"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYes
commentIdYes

Output Schema

NameRequiredDescriptionDefault
rootIdYes
commentYes
fileKeyYes
cascadeConfirmedYes
deletedCommentIdYes
inferredAffectedReplyIdsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, yet the description adds real value beyond them: cascade behavior (deleting a root may also remove replies), the confirmed-vs-inferred distinction in the result, and the authorization requirement. It does not discuss failure behavior for already-deleted or non-authored comments, which is the remaining gap for a destructive operation.

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?

Four short sentences, front-loaded with the DESTRUCTIVE WRITE label, then cascade risk, then return semantics, then authorization. No filler and the riskiest information comes first.

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?

With an output schema present the description needn't detail return fields, and annotations cover the safety profile; the description still adds cascade and authorization context. The main omission is any explanation of the "file" parameter, which is required for every call.

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

Parameters2/5

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

Schema description coverage is 0% and there are two required parameters, so the description must carry the load. It only implicitly characterizes commentId (must be an explicit ID) and never mentions the "file" parameter at all, leaving its meaning and format undocumented in both places.

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

Purpose4/5

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

States a specific verb and resource ("permanently delete the explicit comment ID") plus the acting scope ("as its author"), which lets an agent distinguish this single-target delete from a bulk delete. It stops short of naming the sibling it is not (e.g. figma_delete_comments), so the differentiation is inferred from "explicit comment ID" rather than stated.

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

Usage Guidelines3/5

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

The prerequisite "Requires explicit user authorization" tells the agent a precondition exists, and "explicit comment ID" implies this is for a known single comment. However, there is no explicit when-to-use vs when-to-use-the-bulk-alternative guidance, and no statement of what to do if only a thread/reply handle is known.

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