Copilot Counterpart

Overview Schema Source Related Servers Discussions Admin

copilot_orchestrate

Opt in to model-initiated recursive delegation, letting an orchestrating model spawn bounded child tasks across model families with tree-wide limits, then manage the returned job via standard event, cancel, and forget calls.

Instructions

Opt in to model-initiated recursive delegation through the router. Context only: no files, shell or network tools. Explicit model selects the lead only; children route independently. Limits cover the whole tree including waiting parents. Usage thresholds are soft, not a spend cap. Use ordinary copilot_events/cancel/forget on the returned job.

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": {
      "requestId": "<requestId>",
      "prompt": "<prompt>",
      "sharingAuthorized": "<sharingAuthorized>"
    },
    "name": "copilot_orchestrate"
  }
}

Input Schema

Name	Required	Description	Default
`risk`	No		low
`role`	No		analysis
`model`	No
`limits`	No
`prompt`	Yes
`requestId`	Yes
`complexity`	No		normal
`leadFamily`	No	Model family of the orchestrating assistant (Codex: openai, Claude: anthropic). Reviews prefer the other family. Defaults to the server's COPILOT_COUNTERPART_LEAD_FAMILY.
`timeoutSeconds`	No
`reasoningEffort`	No
`sharingAuthorized`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.0Nov 15, 2026

TDQS

B3.4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: context-only capability ('no files, shell or network tools'), that limits span the whole tree including waiting parents, and that usage thresholds are soft rather than a spend cap. It omits permission/authorization requirements, whether the opt-in is persistent or per-call, and what happens when limits are hit mid-tree.

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?

Five tight sentences with no filler; purpose is front-loaded and each clause carries distinct information. The telegraphic style assumes familiarity with the router's terminology, which costs some first-read clarity.

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?

For a complex, annotation-free, output-schema-free tool with 11 parameters including a nested limits object, the description covers purpose, capability boundaries, limit semantics and follow-up lifecycle. It still leaves the required sharingAuthorized const, timeouts, and the shape of the returned job undocumented beyond a single passing mention.

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 only 9% across 11 parameters, so the description must compensate and it partially does: it clarifies the nested 'limits' object (tree-wide scope, not a spend cap) and the 'model' parameter (selects the lead only; children route independently). The remaining parameters, including requestId, prompt, sharingAuthorized, role, risk, complexity, timeoutSeconds and reasoningEffort, get no meaning from the description.

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?

States a specific action and resource: 'Opt in to model-initiated recursive delegation through the router', which is distinguishable from explicit delegation siblings like copilot_delegate. It does not name a sibling directly, but the 'model-initiated' vs explicit-model distinction gives an agent a workable read on what this tool is for.

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?

Gives follow-up routing ('Use ordinary copilot_events/cancel/forget on the returned job') but never states when to choose this over copilot_delegate or copilot_start, nor when to avoid it. Usage context is implied by 'opt in' rather than spelled out.

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

Deploy Server