Skip to main content
Glama

resolve_escalation

Idempotent

Answer an agent escalation by deciding, convening a huddle, retrying, reassigning, amending, dismissing, or awaiting human action so the requester can resume.

Instructions

Answer an escalation the watcher woke you for (execution_status(view: "escalations") lists them). action: decide (decision is the answer, delivered to the requester, who resumes), huddle (a format with participants: micro by default, or meeting, collaborate, debate, waffle-house, conversation, replan, ultraplan; calls the provider), retry, reassign (participants[0] takes the task over), amend (amendment is a merge patch of the contract), dismiss, or await_human (only when the human must act). resolved_by defaults to the contract's orchestrator. An escalation already resolved is returned unchanged. The runner applies any resume, retry or stop on its next tick.

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": {
      "execution_id": "<execution_id>",
      "escalation_id": "<escalation_id>",
      "action": "<action>"
    },
    "name": "resolve_escalation"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoModel id. Defaults: claude-sonnet-5-5 (anthropic), gpt-5.6-luna (openai), zai-org/GLM-5.3 (together), qwen/qwen3-235b-a22b-instruct-2507 (replicate), qwen3:14b (ollama), default (openai_compatible). Model aliases: "opus" (claude-opus-5-5), "sonnet" (claude-sonnet-5-5), "haiku" (claude-haiku-5-5). Replicate accepts owner/name, owner/name:version, or a https://replicate.com/owner/name URL.
actionYesdecide, huddle, retry, reassign, amend, dismiss or await_human.
formatNohuddle: the format (default micro).
base_urlNoOnly with provider "openai_compatible": base URL of an OpenAI-compatible /v1 endpoint (e.g. http://localhost:1234/v1). Overrides OPENAI_COMPATIBLE_BASE_URL. OPENAI_COMPATIBLE_API_KEY, if set, is sent only to the OPENAI_COMPATIBLE_BASE_URL origin or one listed in ROUNDTABLE_OPENAI_COMPATIBLE_TRUSTED_ORIGINS; any other base URL gets no Authorization header and must be https (http only to loopback, or to private addresses with ROUNDTABLE_ALLOW_PRIVATE_BASE_URLS=1), never a cloud metadata or (without that setting) private address.
decisionNodecide: the answer; otherwise the resolution text the requester sees.
providerNoLLM provider. Default: anthropic. Options: anthropic, openai, together, replicate, ollama (local, when reachable), openai_compatible (set OPENAI_COMPATIBLE_BASE_URL or pass base_url).
amendmentNoamend: an RFC 7396 merge patch of the contract (as for amend_contract).
resolved_byNoWho resolves: the contract's orchestrator (default) or its lead.
execution_idYesThe heads-down run (exe-…), as execute or execution_status returned it.
participantsNohuddle: the personas taking part; reassign: [the persona taking the task over].
escalation_idYesThe escalation (esc-…).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

TDQS

A4.5/5.0
Behavior5/5

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

Goes well past the annotations: it discloses that decisions are delivered to the requester who then resumes, that huddle calls the external provider (consistent with openWorldHint), that an already-resolved escalation is returned unchanged (consistent with idempotentHint=true), and that resume/retry/stop are applied asynchronously by the runner on its next tick. That last point is essential timing information an agent cannot get from the schema.

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?

Front-loaded with the purpose before the action detail, and dense rather than padded. The long inline enumeration of huddle formats partly duplicates the format enum and makes the second sentence unwieldy, but no sentence is wasted.

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?

For an 11-parameter, seven-action mutation tool with no output schema, the description covers what each action does, the asynchronous side effects, and idempotency behavior. It leaves the semantics of the individual huddle formats (micro vs. meeting vs. debate vs. ultraplan) unexplained, which matters given an enum of eight unfamiliar values with sibling tools like end_meeting and end_ultraplan in play.

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?

Schema coverage is 100%, so the baseline is 3, but the description consolidates action-conditional parameter meaning in one place: decision as the answer that also resumes the requester, participants[0] as the reassign target, amendment as an RFC 7396 merge patch, and resolved_by defaulting to the contract's orchestrator. Most of this echoes the schema, so the added value is modest rather than transformative.

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?

Opens with a specific verb and resource — 'Answer an escalation the watcher woke you for' — then enumerates the seven actions and what each does semantically. An agent can distinguish this from siblings like escalate, control_execution, or amend_contract without opening any schema.

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?

Provides an explicit routing hint to execution_status(view: "escalations") for discovering pending escalations, and gives per-action usage glosses including one hard exclusion ('await_human (only when the human must act)'). It stops short of stating when to prefer retry over reassign or amend over decide, so selection among competing actions still requires inference.

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