Skip to main content
Glama

Agent mode set

agent_mode_set

Moves an agent's switch, as the owner would on Agents: paused, ask (show me each) or own (on its own). Only where the switch changes something for that agent (input.app.agents says what each one's switch does): for one whose switch only pauses, paused pauses it and own switches it back on, and ask is refused; one with no switch is refused with where its own controls are. It never starts an agent that has not been started. Returns the change and the agent as it now stands. It needs an act key.

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": {
      "id": "<id>",
      "mode": "<mode>"
    },
    "name": "agent_mode_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesthe agent's id
modeYesown: it learns from the owner's first few answers, then works on its own (where the owner said the business's work runs on its own, no learning: what the owner's answers cover goes from the start, and the rest asks); ask: it shows the owner each piece first, and what it had lined up comes back as a card; paused: it stops, and what it already had waiting is held until switched back
projectNoThe project's id or exact name. Optional when the account has one project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare this is not read-only and not destructive, and the description adds substantive behavior beyond them: an act key is required, the call never starts an unstarted agent, certain modes are refused per-agent, and it returns the change plus the agent's current state. The phrasing 'Moves an agent's switch' is also usefully non-destructive in tone, matching destructiveHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence carries information, but the middle sentence is a long run-on clause chain ('for one whose switch only pauses, paused pauses it and own switches it back on, and ask is refused; one with no switch is refused with where its own controls are') that burdens parsing. The key action and the auth requirement are split across the opening and closing sentences rather than front-loaded together.

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 three-parameter mutation with no output schema, the description covers the failure modes, the auth prerequisite, and the return shape (the change and the agent as it now stands). What remains unstated is what the agent should read first to learn which switch behavior applies, leaving a small gap in the call sequence.

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 100% and the mode enum already carries a long per-value explanation, so the description's restatement of paused/ask/own semantics adds little beyond the schema. The one genuine addition is the conditional rule that ask is refused where the switch only pauses, which the schema does not encode.

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?

The description names a specific verb and resource (moving an agent's switch) and enumerates the three target states (paused, ask, own), so the operation is unambiguous. It also implicitly separates itself from agent_open-style tools by stating it never starts an agent that has not been started, though it never names a sibling directly.

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?

It gives real conditions: only where the switch changes something for that agent, ask is refused for pause-only switches, and agents with no switch are refused with a pointer to their own controls. What it lacks is an explicit pointer to agents_read or input.app.agents as the place to check before calling, so the agent is told the prerequisite data exists but not the tool that fetches it.

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.