Skip to main content
Glama
Sign In
Codex Discussion MCP

Codex Discussion MCP

by smallmiro
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Forget retained local discussion output

discussion_forget
Idempotent

Release inactive discussion output retained in this MCP process without deleting saved history or canceling generation; rejects active or uncertain work and invalidates old cursors.

Instructions

Explicitly release inactive discussion output retained in this MCP process. Does not delete saved Codex history, cancel generation, or run inference. Rejects active, pending, loading, or uncertain connection-lost work. Returns forgotten=false for an unknown or already released local discussion. Old cursors become invalid; read without a cursor to resume saved history while connected. Received output otherwise remains retained until process exit.

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": {
      "discussionId": "<discussionId>"
    },
    "name": "discussion_forget"
  }
}

Input Schema

NameRequiredDescriptionDefault
discussionIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.5

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations, the description explains exactly what is released, what is not affected (saved Codex history, generation, inference), rejection conditions, the forgotten=false return case, cursor invalidation, and the retention-until-process-exit behavior. This gives the agent substantial behavioral context for a non-destructive but state-changing local operation.

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 is front-loaded with the core action and then layers in exclusions, failure cases, and cursor behavior. It is dense but mostly purposeful; a few sentences, such as the final retention note, could be tightened without losing meaning.

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 single-parameter tool with no output schema, the description covers the action, what is not affected, rejection states, return signaling, and follow-up behavior after cursor invalidation. Nothing essential for correctly invoking or interpreting the tool appears to be missing.

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?

The schema has 0% description coverage for the single discussionId parameter, so the description should compensate. It implies the parameter identifies a local discussion and mentions unknown or already released discussions, but it does not explicitly define the identifier, where to obtain it, or its relationship to saved history. The compensation is helpful but incomplete.

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 description states a specific verb and resource: explicitly releasing inactive discussion output retained in this MCP process. It also distinguishes the action from deletion, cancellation, and inference by negation, so an agent can understand what this tool does without 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?

The description clearly specifies when the tool will reject the call: active, pending, loading, or uncertain connection-lost work. It also explains the fallback of reading without a cursor to resume saved history while connected. However, it does not explicitly compare this tool with discussion_cancel or discussion_read, so the alternative-selection guidance is implied rather than fully explicit.

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