mcp-chatgpt

chatgpt_get_latest_response

Retrieve the most recent assistant reply from a ChatGPT conversation after a timeout or page reload, without sending a new prompt. Optionally refresh the page or specify a conversation ID to recover the answer.

Instructions

Fetch and recover the latest assistant response (including text, code blocks, and images) from the current or specified conversation without asking a new question. Useful after recovering from a timeout or reload.

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": "chatgpt_get_latest_response"
  }
}

Input Schema

Name	Required	Description	Default
`refresh_first`	No	Whether to reload the page before reading the latest response (default: true).
`conversation_id`	No	Optional conversation ID or URL to fetch the latest answer from.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Aug 20, 2026

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description carries the disclosure burden. It mentions that the tool does not ask a new question and returns text, code blocks, and images, but it omits side-effect context like the default page reload implied by refresh_first and possible failure modes.

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?

Two sentences with the main purpose front-loaded. It communicates function, content, scope, and use case with no wasted words.

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?

For a simple retrieval tool with no output schema, it adequately describes what is returned, when to use it, and conversation scope. It could mention failure conditions or authentication dependencies, but these are not essential for this complexity.

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% for both parameters, so the schema already documents refresh_first and conversation_id well. The description adds 'current or specified conversation' and timeout/reload context, but does not substantially extend parameter meaning beyond 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?

Description uses a specific verb ('Fetch and recover') with a clear resource ('latest assistant response') and scope ('current or specified conversation'). It distinguishes from siblings by noting 'without asking a new question', separating it from chatgpt_ask and other conversation tools.

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?

Provides an explicit use case: 'Useful after recovering from a timeout or reload.' It implicitly discourages use for new questions, but does not explicitly name alternatives like chatgpt_ask or chatgpt_reload.

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

Deploy Server