Skip to main content
Glama

AINDEX

Change how much an agent may do alone

set_agent_mode
Idempotent

Change an agent's mode: auto (on its own, following its strategy) or propose (the older ask-first mode, for an agent that still uses it). An agent with its own wallet has no watch mode: to halt it, use stop_agent. Open to some accounts only. Needs an access key that may act. Confirm with the person before choosing auto.

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": "<agent>",
      "mode": "<mode>"
    },
    "name": "set_agent_mode"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes
agentYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already cover idempotency and non-destructiveness; the description adds real operational context not in structured data: limited account eligibility, a required access key with acting authority, and a requirement to confirm with the person before selecting auto. That confirmation/clarification-of-intent guidance is the valuable part. It does not say whether the change is reversible or how to revert from auto, which for a mode switch is worth stating.

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?

Short, front-loaded, and every sentence carries information: mode meanings, the watch exception, the stop_agent alternative, access constraints, and the confirm-before-auto rule. Slightly telegraphic phrasing ("Open to some accounts only") costs a little clarity, but there is no filler.

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 two-parameter mutation tool with no output schema, the definition covers auth, eligibility, safety-of-choice, and the halting alternative, which is most of what an agent needs. What's missing is the meaning of the 'watch' enum value and any statement about the result of the call or reversibility.

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 description coverage is 0%, so the description must carry parameter meaning. It explains 'auto' and 'propose' but leaves 'watch' undefined despite it being a valid enum value, and says nothing about the 'agent' parameter beyond the fact that some agents can't use watch and that a capable access key is needed. Partial compensation for a zero-coverage schema.

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 verb+resource ("Change an agent's mode") and immediately disambiguates two of the enum values, auto vs. propose. It is clearly distinct from stop_agent, which it names. The gap is 'watch', which is only referenced obliquely ("An agent with its own wallet has no watch mode") without ever being defined, so one of the three accepted values is described only by negation.

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 explicit routing guidance: use stop_agent to halt an agent rather than this tool, and describes the tradeoff between auto and propose. It stops short of a full when-not rule (e.g., which agents actually support propose, which support watch), but the alternative and the condition selecting it are stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources