Skip to main content
Glama

chatgpt

Send prompts to ChatGPT and get replies with a conversation ID to continue multi-turn chats, list prior conversations, attach images, or enable web search. Runs in the background without an API key.

Instructions

Ask ChatGPT a question (runs in the background through the Codex CLI signed in with the user's ChatGPT plan; no API cost, does not touch the screen). Operations: 'ask' sends a prompt and returns ChatGPT's reply plus a conversation_id you can pass back to continue the same conversation; 'get_conversations' lists conversations started through this tool. ChatGPT here has no access to files, email, or other apps; include any text it needs in the prompt.

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": {
      "operation": "<operation>"
    },
    "name": "chatgpt"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoModel (default gpt-6.2-sol)
imagesNoOptional local image file paths to attach
promptNoThe prompt to send to ChatGPT (required for ask)
operationYes'ask' or 'get_conversations'
web_searchNoLet ChatGPT search the web for this answer (default false)
conversation_idNoOptional conversation_id from an earlier ask, to continue that conversation
timeout_secondsNoMax seconds to wait (default 600)
reasoning_effortNoReasoning effort (default medium)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description supplies substantial behavioral context: background execution, signed-in ChatGPT plan, no API cost, no screen interaction, and no access to files/email/apps. It also discloses that 'ask' returns a reply plus a conversation_id for continuation and that 'get_conversations' lists conversations started through this tool. It stops short of covering rate limits, failure behavior, or side effects of starting a conversation, so it is not a 5.

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?

The description front-loads purpose and operations in a compact set of sentences; the parenthetical about Codex CLI and cost is useful context rather than filler. There is slight redundancy between 'Ask ChatGPT a question' and the operation descriptions, which keeps it from a 5.

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 an eight-parameter tool with no annotations and no output schema, the description covers execution environment, data-access limits, both operations, and ask's return value/conversation continuation. It does not detail get_conversations output shape or error/timeout behavior, leaving minor 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 description coverage is 100%, so all eight parameters are already documented in the schema. The description adds some meaning for conversation_id and prompt, but leaves model, images, web_search, timeout_seconds, and reasoning_effort to the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

States a specific action (ask ChatGPT a question) and enumerates two distinct operations, 'ask' and 'get_conversations,' with their outcomes. An agent can tell what the tool does and which operation to invoke without ambiguity.

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?

Explains operational context and constraints: runs in the background via Codex CLI signed in with the user's ChatGPT plan, has no API cost, does not touch the screen, and has no access to files/email/apps unless text is included in the prompt. It does not explicitly frame when to prefer this tool over external alternatives, but there are no sibling tools and the operation split is clear.

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