Skip to main content
Glama

Steer a running Codex turn

codex_steer

Add instructions to the turn Codex is currently working on without stopping it. Steer an active run mid-task and optionally wait for a progress snapshot.

Instructions

Add instructions to the turn Codex is currently working on, without stopping it.

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": {
      "thread_id": "<thread_id>",
      "prompt": "<prompt>"
    },
    "name": "codex_steer"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYes
thread_idYes
wait_secondsNoSeconds to block before returning a progress snapshot (default 120). Returns early when the turn finishes or Codex needs an answer. The turn keeps running after this returns.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It discloses one meaningful behavioral trait—that the running turn is not stopped—but omits what happens if no turn is active, how the added instructions are applied, and what the response contains (the schema hints at a progress snapshot for wait_seconds only).

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?

A single, front-loaded sentence with no wasted words. The core action and its key constraint are immediately clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a mutation-like action on a live agent turn with zero annotations, no output schema, and two undocumented parameters. The one-sentence description is too thin for the complexity, leaving failure modes and parameter roles unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33%; only wait_seconds is documented in the schema. The description adds no meaning for thread_id or prompt, leaving the agent without guidance on required identifiers or the nature of the injected prompt.

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 uses a specific verb ('add instructions') and resource ('the turn Codex is currently working on'), making the action distinguishable from starting a new turn. It implicitly contrasts with stopping the turn, though it never names codex_interrupt or codex_respond explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'without stopping it' implies when this is appropriate versus an interrupt, but there is no explicit statement of preconditions (e.g., a turn must be active) or named alternatives. An agent must infer the selection criteria from context.

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