Skip to main content
Glama
buidangminh23

codex-mcp-bridge

by buidangminh23
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Start a new Codex thread

start_codex_thread
Destructive

Launch a new Codex task in a chosen working directory, with an optional title, model, and starting prompt, to run independent work in its own separate thread.

Instructions

Start a new Codex task when the user explicitly or through standing instructions authorizes a new conversation for independent work. In Desktop mode include the initial prompt and a fresh requestId to create and assign a visible task atomically; keep requestId unchanged on retries. Continue unfinished work with send_to_codex_thread and its original threadId. Use delegate_to_codex to also wait for its reply.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdYesAbsolute working directory for the new Codex session
nameNoOptional title to show for the new Codex session
modelNoModel override, e.g. gpt-5.6-luna
promptNoInitial task; required with CODEX_BRIDGE_DESKTOP_TASKS=1, starts immediately. The prompt for the recipient agent, in English with the sections Goal, Context, Task, Scope, Constraints, Done when, Reply format (omit any that do not apply); text the user supplied is sent verbatim
requestIdNoDesktop creation identity: fresh UUID per independent task, same UUID on retries. Omit only for legacy title/prompt deduplication. Not supported in legacy app-server mode.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.19.3
    • addedInput schema / properties / requestId
      Added value: +{
+  "description": "Desktop creation identity: fresh UUID per independent task, same UUID on retries. Omit only for legacy title/prompt deduplication. Not supported in legacy app-server mode.",
+  "format": "uuid",
+  "type": "string"
+}
  2. Changed1 schema field changedv1.18.0
    • changedInput schema / properties / prompt / description
      Previous value: -"Initial task; required with CODEX_BRIDGE_DESKTOP_TASKS=1, starts immediately"New value: +"Initial task; required with CODEX_BRIDGE_DESKTOP_TASKS=1, starts immediately. The prompt for the recipient agent, in English with the sections Goal, Context, Task, Scope, Constraints, Done when, Reply format (omit any that do not apply); text the user supplied is sent verbatim"
  3. Changed1 schema field changed
    • addedInput schema / properties / prompt
      Added value: +{
+  "description": "Initial task; required with CODEX_BRIDGE_DESKTOP_TASKS=1, starts immediately",
+  "minLength": 1,
+  "type": "string"
+}
  4. First observedv1.11.2

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true, idempotentHint=false. The description adds operational details beyond annotations: Desktop mode atomic creation, requestId handling on retries, and that the tool creates a visible task. However, it does not elaborate on why it's destructive or what side effects occur beyond task creation.

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?

Three sentences, front-loaded with the core action and condition, then routing guidance. Every sentence earns its place and there is no redundancy.

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?

Given the tool's complexity (creates a new thread, multiple parameters, mutation), the description covers usage conditions, alternatives, and key behavioral traits. It lacks details on error handling or what happens on failure, but with full schema coverage and annotations, it is largely complete.

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%, so the schema already documents all parameters thoroughly. The description mentions 'initial prompt' and 'fresh requestId' behavior, which aligns with schema but adds minimal semantics beyond it (e.g., retry consistency). Baseline 3 is appropriate when schema does the heavy lifting.

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

Purpose4/5

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

The description states a specific action: 'Start a new Codex task' and clearly indicates it creates a new thread. It distinguishes itself from siblings by explicitly naming send_to_codex_thread and delegate_to_codex and describing when to use each alternative.

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?

It provides explicit guidance: use when the user explicitly or through standing instructions authorizes a new conversation; use send_to_codex_thread to continue unfinished work with an original threadId; use delegate_to_codex to also wait for a reply. This covers when to use this tool vs alternatives.

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