Skip to main content
Glama

Start a local CLI subagent

start_agent
Destructive

Launch a subagent with a self-contained prompt in a specified working directory, returning an invocation ID you can use later with wait_agent to monitor the outcome.

Instructions

Start one subagent and return its in-memory invocation ID without waiting for completion.

Use wait_agent with the returned ID to observe the invocation. The launched provider may read, write, or run commands in cwd subject to its native permission controls.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdYesAbsolute existing directory where the subagent runs.
promptYesComplete, self-contained task for the subagent.
providerYesLocal subagent provider to launch.
session_idNoProvider session ID returned by an earlier finished invocation.
timeout_secondsNoMaximum provider runtime in seconds.
provider_optionsNoExplicit provider-native options. Omit to inherit the provider's own settings; supported keys depend on the selected provider.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
stateYes
invocation_idYes
Behavior5/5

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

The description states that the launched provider may read, write, or run commands in cwd subject to native permission controls, which meaningfully expands on the annotations' destructiveHint and openWorldHint. It also discloses the non-blocking behavior, helping the agent understand the tool's side effects before invoking it.

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 description is compact and front-loaded: the first sentence establishes the essential behavior, and the second sentence provides the key follow-up action and side-effect warning. Every sentence earns its place.

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?

The description covers the critical non-blocking launch behavior, required follow-up with wait_agent, and potential destructive effects. An output schema exists, so the return value does not need to be described. Minor gaps like when to use cancel_agent remain, but they are not essential for correct invocation.

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 100%, and each parameter already carries a meaningful description. The tool description adds no new parameter-level semantics, so the baseline of 3 is appropriate.

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 clear verb ('Start'), the resource ('one subagent'), and the key outcome ('return its in-memory invocation ID without waiting'). This sharply distinguishes start_agent from its wait_agent and cancel_agent siblings.

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?

The description explicitly tells the agent to use wait_agent with the returned ID to observe the invocation, which is the natural alternative workflow. This is direct, actionable guidance for choosing and sequencing this tool.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TimWongUp/agentnave'

If you have feedback or need assistance with the MCP directory API, please join our Discord server