Skip to main content
Glama

Ask my owner

escalate_to_human
Destructive

Records an owner decision request for a thread, marks it input-required, and returns the question to ask your owner without messaging anyone; relay only approved updates.

Instructions

Use when a thread needs your owner's decision. Records an escalation, marks the thread input_required, and returns ask_owner: the question for YOU to ask your owner. It does not message anyone itself. Afterwards relay only what the owner approved (post_update, set_status: 'active').

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>",
      "question": "<question>"
    },
    "name": "escalate_to_human"
  }
}

Input Schema

NameRequiredDescriptionDefault
contextNo
questionYes
thread_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With readOnlyHint=false and destructiveHint=true already declared, the description adds real context: the thread is mutated to input_required, and the return value is a question string the caller must relay rather than a delivered message. It does not address why the call is destructive or what happens on a repeat call despite idempotentHint=false.

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?

Three tight sentences, front-loaded with the usage trigger, followed by effect and return value, then the required follow-up. Nothing is redundant or padding.

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?

Compensates for the missing output schema by naming the returned `ask_owner` value and explaining the relay obligation, which is what an agent most needs. The remaining gap is the undocumented `context` parameter on a mutation tool with no annotations explaining its destructive and non-idempotent characteristics.

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 0%, so the description must carry the parameter meaning. It only gestures at `question` ('the question for YOU to ask your owner') and never explains `context` (up to 2000 chars) or what `thread_id` must reference, leaving two of three parameters undocumented anywhere.

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?

States a specific verb and resource: records an escalation, marks the thread input_required, and returns an `ask_owner` question string. It also draws the key boundary ('It does not message anyone itself'), which separates it from the sibling messaging tools like post_update.

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?

Gives a clear trigger ('when a thread needs your owner's decision') and an explicit follow-up path after approval (post_update, set_status: 'active'), plus a negative boundary that the tool does not message anyone. It lacks an explicit 'do not use when…' case, e.g. when the decision is already known or the owner is reachable directly.

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