Skip to main content
Glama
Minidoracat

mcp-feedback-enhanced

by Minidoracat
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Interactive Feedback

interactive_feedback

Collect user feedback during LLM agent tasks to adjust behavior and confirm next steps. Enables iterative interaction via Web UI or desktop app with timeout and summary.

Instructions

Interactive feedback collection tool for LLM agents.

USAGE RULES:

  1. During any process, task, or conversation, whether asking, replying, or completing phased tasks, you must call this tool to ask for feedback.

  2. Unless receiving termination instructions, or this tool returns a "no user response" result, all steps must repeatedly call this tool.

  3. Whenever user feedback is received, if the feedback content is not empty, you must call this tool again and adjust behavior based on the feedback content.

  4. You can stop calling this tool, and the process is considered complete, when the user explicitly indicates "end" or "no more interaction needed", or when this tool returns a "no user response" result (the wait timed out or the user closed the feedback UI) — in that case finish the task and do NOT call this tool again.

  5. You should summarize what have done, and provide project directory through args to let user know what you have done to provide feedback for next step.

Input Schema

NameRequiredDescriptionDefault
summaryNoAI 工作完成的摘要說明我已完成了您請求的任務。
timeoutNo等待使用者回饋的逾時時間（秒）。有效範圍 60–86400；超出範圍會由伺服器端鉗制，因為使用者需要實際可用的回饋時間。
project_directoryNo專案目錄路徑.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.8.5
    • changedInput schema / properties / timeout / description
      Previous value: -"等待用戶回饋的超時時間（秒）。有效範圍 60–86400；超出範圍會由伺服器端鉗制，因為使用者需要實際可用的回饋時間。"New value: +"等待使用者回饋的逾時時間（秒）。有效範圍 60–86400；超出範圍會由伺服器端鉗制，因為使用者需要實際可用的回饋時間。"
  2. Changed2 schema fields changedv2.6.2
    • changedInput schema / properties / timeout / description
      Previous value: -"等待用戶回饋的超時時間（秒）"New value: +"等待用戶回饋的超時時間（秒）。有效範圍 60–86400；超出範圍會由伺服器端鉗制，因為使用者需要實際可用的回饋時間。"
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "result": {
-      "items": {},
-      "type": "array"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "type": "object",
-  "x-fastmcp-wrap-result": true
-}New value: +null
  3. First observedv2.6.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the two behaviors that matter most: the call blocks waiting on a human, and it can return a 'no user response' result when the wait times out or the user closes the feedback UI. It also reveals that a feedback UI is presented to the user, which is a real side effect. It omits what the returned feedback payload looks like and whether server-side clamping of timeout changes the effective wait.

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

Conciseness3/5

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

The numbered-rule structure is front-loaded and scannable, but the block is long for a 3-parameter tool and rules 2 and 4 overlap heavily (both describe when to stop calling). Rule 3's phrasing 'you must call this tool again' after receiving feedback is redundant with rule 2's repeat instruction.

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?

There is no output schema, so the description should explain return semantics; it partially does via the 'no user response' outcome, but never describes the shape of a successful feedback response. For a zero-required-parameter, blocking, human-in-the-loop tool the description covers the essential lifecycle (when to call, how to loop, how to terminate) and only leaves the success payload unspecified.

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 description coverage is 100%, so both the summary and timeout semantics (including the 60-86400 clamp) are already documented in the schema. The description only adds light framing in rule 5, telling the agent to put a summary of completed work and a project directory into the args so the user has context. That is a useful intent hint but not a semantic detail the schema lacks, so baseline 3 applies.

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

Purpose3/5

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

The opening line 'Interactive feedback collection tool for LLM agents' names the resource but restates the name/title almost verbatim, and never says plainly what invoking it does (block and wait for a human to type feedback in a UI). The numbered rules imply the behavior indirectly, but an agent must infer 'this call pauses and surfaces a prompt to the user' from fragments like 'wait timed out' and 'user closed the feedback UI'.

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?

Rules 1-4 give explicit triggering conditions ('during any process... you must call this tool'), explicit loop behavior ('all steps must repeatedly call this tool'), and explicit stop conditions ('user explicitly indicates end', 'no user response'). Alternatives are implicitly excluded since the only sibling, get_system_info, is unrelated, so no routing ambiguity remains. The only weakness is verbosity/repetition between rules 2 and 4.

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