Skip to main content
Glama
Sign In
ThriftyRelay

ThriftyRelay

by Roseu7
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Wait for Remote Task

remote_inspect
Destructive

Check an async Codex task, wait up to 120 seconds for completion, retrieve stored output, or request cancellation by task ID.

Instructions

After submitting async work, call with task_id only. Waits up to 120s and returns immediately on completion. Finished Codex tasks include answer/review/usage; do not fetch them again. If still running, call again with the same ID without progress polling or repeated commentary. wait_ms=0 is an immediate diagnostic snapshot. step_index retrieves specific stored output. Exposed read/call images return as MCP image content; text character limits apply only to text, with image limits of 8 MiB/4 images per task. action=cancel requests task cancellation immediately; ending a wait never cancels the task. Never resubmit unknown writes.

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>"
    },
    "name": "remote_inspect"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNoinspect
task_idYes
wait_msNo
max_charsNo
step_indexNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.1

TDQS

A4.8/5.0
Behavior5/5

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

The description adds substantial context beyond the annotations: it explains the 120s wait behavior, immediate return on completion, that ending a wait never cancels the task, that cancellation requires action=cancel, and that finished Codex tasks include answer/review/usage. It also discloses image content limits and text character limits. This is rich behavioral detail that the structured fields do not provide.

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 dense but front-loaded with the core instruction, and most sentences earn their place by adding operational constraints. It becomes somewhat compressed and run-on in the middle, especially around image limits and task output details, but it is not bloated or off-topic.

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 five-parameter async task tool with no output schema and no schema descriptions, the definition is unusually complete. It covers waiting, re-inspection, diagnostics, cancellation, step retrieval, returned content types, and limits, leaving little an agent needs in order to call it correctly.

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

Parameters4/5

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

With 0% schema description coverage, the description does most of the work: it explains task_id usage, wait_ms=0 as an immediate diagnostic snapshot and the 120s cap, step_index retrieval of specific stored output, and action=cancel semantics. However, max_chars is only indirectly referenced through the text character-limit sentence and is never named or explicitly described.

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: wait for and inspect a remote async task, returning immediately on completion. It clearly distinguishes itself from the submission sibling by saying 'After submitting async work, call with task_id only' and covers both inspect and cancel modes. An agent can identify the tool 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 Guidelines5/5

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

It gives explicit when-to-use guidance: call after submitting async work, use task_id only, call again with the same ID if still running. It also names specific alternatives and exclusions: do not fetch finished Codex tasks again, use wait_ms=0 for immediate diagnostics, use action=cancel for cancellation, and never resubmit unknown writes.

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