Skip to main content
Glama

Flag an Operations lane as needing the operator

raise_human_action

Escalate a genuine blocker that no agent seat can resolve alone by submitting the required ask, reason, and prior attempts, then clear it once resolved.

Instructions

ONLY for an absolute brick wall - something no seat can do with its own reach. Requires reason to be one of the recognised walls, and tried_instead to say what you already attempted: your shell, remote access to the fleet, the vault, the forge, the tool catalog, the other seats. Most walls are not walls. This is the one column that costs the operator time, so a lazy entry is worse than no entry. Clear it with clear_human_action the moment it is resolved.

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": {
      "agent_id": "<agent_id>",
      "lane": "<lane>",
      "ask": "<ask>",
      "why": "<why>",
      "reason": "<reason>",
      "tried_instead": "<tried_instead>"
    },
    "name": "raise_human_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
askYesThe one thing to do, in plain words.
whyYesWhy it cannot be done without a person.
laneYesRef (AP-01) or lane id (boardroom).
reasonYesOne of the recognised walls. list_lanes with include_induction returns the list.
agent_idYes
tried_insteadYesWhat you already attempted with your own reach. Short answers are rejected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.11

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write action. The description adds important consequence context beyond annotations: this entry costs operator time, and a lazy entry is worse than no entry, which discourages low-quality submissions. It could say more about duplicate handling or exactly what raising the action produces, but the key behavioral cost is disclosed.

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?

The critical constraint is front-loaded in the first clause, and every subsequent sentence adds operational value: eligibility, required fields, cost of misuse, and cleanup. There is no filler or repetition.

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 a six-required-parameter mutation-style tool with no output schema, the description covers when to use it, what must be attempted first, how to satisfy reason and tried_instead, and how to clear it later. It is sufficient for correct invocation, though it does not describe what the operator-facing entry looks like after creation or how duplicates are treated.

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 high at 83%, so the schema already documents most parameters. The description adds meaningful semantics for the two most judgment-heavy fields: reason must be one of the recognised walls, and tried_instead must describe actual prior attempts, with categories of reach listed. It does not elaborate on lane, ask, why, or agent_id, but those are covered by the schema.

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 action and scope: flagging an Operations lane as needing the operator, but only for an 'absolute brick wall' no seat can handle. It also explicitly routes away from overuse and names clear_human_action as the cleanup sibling, so an agent can distinguish the operation from routine lane work.

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 criteria, a strong when-not-to-use warning ('Most walls are not walls'), and concrete alternatives to attempt first: shell, fleet remote access, vault, forge, tool catalog, and other seats. It also names the sibling tool to call on resolution, clear_human_action.

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