Skip to main content
Glama
gl-mcp-feedback

gl-mcp-feedback

by youjunxiaji

interactive_feedback

Opens a Web UI to collect user feedback on AI work, plans, or questions, returning text replies or uploaded images. Use it for interactive confirmations and structured question routing.

Instructions

Open a Web UI to collect interactive feedback from the user.

This tool is the PRIMARY communication channel with the user. The full list of "when to call" scenarios lives in the project's gl-mcp-feedback user rules; this docstring covers how to use this tool.

Strict prohibitions: - While this tool is available, DO NOT invoke Cursor's built-in AskQuestion. Route every question through summary as a numbered list. - DO NOT end the turn with a plain-text reply when there is substantive content for the user to read. Put it in summary. - When the user skips without feedback, re-call this tool to ask why; only stop on explicit termination (结束 / 不用了 / stop / done). - Allowed parameters: project_directory, summary, timeout, plus conversation_id, which a Cursor hook fills in: never set it yourself. Names like question / choices / options belong to AskQuestion and will fail schema validation here.

summary writing rules: - Markdown: headings (##), lists, tables, code fences, bold for key decisions. Include modified file paths and explicit questions when applicable. - NEVER pass an empty string or the placeholder phrase 我已完成了您请求的任务。 — runtime validation rejects them and you must re-call with a real summary.

Queued messages: While you work between two calls, the user can keep typing in the Web UI; those messages are queued (at most 3) and reach you in one of two ways, both under a header starting with (你工作期间,用户追加了 N 条消息:

- After any tool call, a Cursor hook appends the queue to that
  tool's result. Images are saved as local files whose paths are
  listed in the block: open them with ``Read``.
- On your next call to this tool, the queue is returned
  immediately, without waiting for a new reply.

Either way they are NOT an answer to the ``summary`` you just
passed: treat them as new instructions in the given order, act on
them, then call this tool again.

Args: project_directory: Absolute or relative project path. Defaults to cwd. summary: Required Markdown summary. No empty string, no placeholder. timeout: Seconds to wait for user feedback. Values above 600 are capped, so always pass 600. conversation_id: Filled in by a Cursor hook. Never set it yourself.

Returns: ToolResult: TextContent with the user's text feedback plus MCPImage objects for any uploaded images. An empty result means the user skipped — re-call to ask why. A result starting with [interactive_feedback TIMEOUT] means the user has not replied within the wait limit — re-call to keep waiting.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "interactive_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
summaryNoMarkdown summary of the AI's current work / plan / question, rendered in the Web UI. MUST be filled in with substantive content; empty strings and placeholder phrases (e.g. "我已完成了您请求的任务。") are rejected at runtime.
timeoutNoSeconds to wait for user feedback. Values above 600 are capped, so always pass 600.
conversation_idNoFilled in automatically by a Cursor hook to identify the conversation. NEVER set this yourself; always leave it empty.
project_directoryNoProject directory path..

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.0.2
    • changedInput schema / properties / timeout / description
      Previous value: -"Seconds to wait for user feedback. Keep >= 600."New value: +"Seconds to wait for user feedback. Values above 600 are capped, so always pass 600."
  2. Changed2 schema fields changedv3.0.1
    • addedInput schema / properties / conversation_id
      Added value: +{
      +  "default": "",
      +  "description": "Filled in automatically by a Cursor hook to identify the conversation. NEVER set this yourself; always leave it empty.",
      +  "type": "string"
      +}
    • removedInput schema / properties / title
      Removed value: -{
      -  "default": "",
      -  "description": "Optional short headline (max ~30 chars) for this feedback round, displayed in the browser tab and at the top of the AI summary panel. Should be concise (e.g. \"需要你提供更多信息\", \"修复完成,请验证\"). Leave empty when there's no good headline.",
      -  "type": "string"
      -}
  3. First observedv2.2.3

TDQS

A4.6/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden and does so: it discloses the ~600s wait cap, that an empty result means the user skipped, that a `[interactive_feedback TIMEOUT]` prefix signals no reply, and that up to 3 queued messages arrive appended to other tool results with images saved as local paths. It also warns which parameter names (question/choices/options) will fail schema validation, which is non-obvious failure mode information.

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?

Well structured with labeled sections (prohibitions, summary writing rules, queued messages, Args, Returns) and the purpose is front-loaded. It loses a point for duplicating schema content almost verbatim in the Args block, notably the 'always pass 600' timeout rule appearing in both the body and the schema description.

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?

For a blocking user-interaction tool with no output schema and no annotations, everything an agent needs is present: what the UI does, required summary quality, wait/timeout semantics, queued-message mechanics, and the three distinct return shapes (feedback, empty skip, TIMEOUT prefix) with the correct follow-up action for each.

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 coverage is already 100%, so the baseline is 3; the description earns above that by adding runtime rules the schema omits — always pass 600 for timeout because higher values are capped, never set conversation_id yourself because a hook fills it, and placeholders like '我已完成了您请求的任务。' are rejected. The project_directory default-to-cwd clarification is minor but consistent.

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 opening sentence names a concrete verb and resource — 'Open a Web UI to collect interactive feedback' — and the body reinforces the scope by calling it the PRIMARY communication channel with the user, which cleanly separates it from the only sibling, get_system_info. An agent knows exactly what this tool is for before opening the schema.

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?

Strong routing guidance: it explicitly bans the alternative (Cursor's AskQuestion) and mandates routing questions through `summary`, and it prescribes recovery behavior on skip, timeout, and queued messages. The one gap is that the actual 'when to call' scenarios are deferred to an external gl-mcp-feedback user-rules doc that the description does not reproduce, so the agent must fetch that context elsewhere.

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

Deploy Server

Other Tools