Skip to main content
Glama

background_request

DestructiveIdempotent

Saves a continuation request for a task owned by another executor, queues prerequisite operations before Codex starts, and wakes it to diagnose failed dependencies.

Instructions

Save a continuation intent even while another executor owns this task. after_operations lists this task's queued operations to finish before Codex starts; failed dependencies also wake it for diagnosis. End the model turn after receiving the saved operation ID. expected_outputs contains only concrete project-relative file paths. Task hold/pause still controls dispatch.

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": {
      "task_id": "<task_id>",
      "revision": "<revision>",
      "instruction": "<instruction>",
      "op_id": "<op_id>"
    },
    "name": "background_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
op_idYes
task_idYes
revisionYes
instructionYes
after_operationsNo
expected_outputsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

Beyond the annotations it adds real behavioral facts: failed dependencies wake the task for diagnosis, hold/pause still gates dispatch, and the caller must yield the turn after the op ID returns. It does not explain the destructiveHint=true annotation — nothing says what state is superseded or overwritten by saving a continuation intent — which is a notable gap for a mutating, open-world tool.

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?

Four tight sentences with no filler, leading with the capability and scope condition before procedural details. The instruction to end the turn sits mid-paragraph and interrupts the parameter explanation, a minor ordering issue rather than wasted text.

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

Completeness3/5

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

An output schema exists, so return-value documentation is rightly omitted, and the core continuation/dispatch flow is described. However, for a destructive, open-world operation with six undocumented parameters, the definition leaves an agent guessing about revision semantics, op_id provenance, and what state a saved intent displaces.

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 coverage is 0%, so the description must carry all parameter meaning, and it covers only two of six: after_operations (queued ops to finish first) and expected_outputs (constrained to concrete project-relative paths). The four required parameters — task_id, revision, instruction, and especially op_id — receive no explanation of format, purpose, or the concurrency role that revision likely plays.

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?

"Save a continuation intent even while another executor owns this task" gives a concrete verb and the distinguishing scope condition (concurrent ownership), which lets an agent recognize the background/continuation case. It never plainly states the outcome in tool-name terms ("request background execution") and does not name the sibling task_background, so differentiation is inferred rather than stated.

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 gives a clear trigger condition (use it even when another executor owns the task) plus a procedural instruction — "End the model turn after receiving the saved operation ID" — and a caveat that task hold/pause still controls dispatch. It stops short of naming alternatives or explicit when-not-to-use cases, so it is clear context without exclusions.

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