Skip to main content
Glama

Crew Manage Tool

crew_manage
Destructive

Set up, manage, and run multi-agent crews that decompose goals across roles using sequential, parallel, or hierarchical processes. Execute tasks asynchronously and check progress.

Instructions

Multi-agent crews — coordinated teams of agents that decompose a goal across roles (sequential, parallel, or hierarchical process). execute is async: it queues ExecuteCrewJob and returns immediately with an execution_id; poll execution_status for progress. Each crew member must be a real agent_id in the same team.

Actions:

  • list / get (read) — list all or fetch one (crew_id).

  • create (write) — name, process_type (sequential|parallel|hierarchical), agents[] (array of {agent_id, role}).

  • update (write) — crew_id + any creatable field.

  • delete (DESTRUCTIVE) — crew_id. Soft-deletes the crew.

  • execute (write — long-running) — crew_id, goal. Reserves budget, returns execution_id.

  • execution_status (read) — crew_id, execution_id. Status, current task, partial results.

  • executions_list (read) — crew_id; optional limit.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: list, get, create, update, execute, execution_status, executions_list
deadline_msNoOptional: max wall-clock time (ms) the tool may spend. If exceeded during the call, returns a DEADLINE_EXCEEDED error. Minimum 100 ms. Leave unset for no deadline.
statusNoFilter by status: draft, active, archived
limitNoMax results to return (default 10, max 100)
crew_idYesThe crew UUID
nameYesCrew name
coordinator_agent_idYesUUID of the coordinator agent
qa_agent_idNoUUID of the QA agent. Optional — when omitted, the coordinator reviews their own work (solo-mode crew).
descriptionNoCrew description
process_typeNoProcess type: sequential, parallel, hierarchical (default: hierarchical)hierarchical
convergence_modeNoHow to determine when the crew is done: any_validated (default), all_validated, threshold_ratio, quality_gate
min_validated_ratioNoFraction of tasks that must be validated when using threshold_ratio mode (e.g. 0.8 = 80%). Default: 1.0
goalYesThe goal/task for the crew to accomplish
execution_idYesThe crew execution UUID
include_full_outputNoInclude full final_output instead of 500-char preview (default false)
Behavior4/5

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

Beyond the destructiveHint annotation, the description discloses behavioral traits: execute is async, returns execution_id, polls via execution_status, includes soft-delete, and reserves budget. This adds significant behavioral context beyond minimal annotations.

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?

The description is well-structured with a clear top-level explanation and bulleted actions. It is concise given the tool's complexity, though some redundancy exists.

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?

Given the 15 parameters, no output schema, and multiple actions, the description provides a fairly complete picture. It covers all actions, async nature, and constraints. Missing details on return values and some parameters, but overall adequate.

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%, so baseline is 3. The description adds context about async behavior and soft-delete for some actions. However, it mentions an 'agents[]' array in the create action that does not correspond to a schema parameter (instead using coordinator_agent_id and qa_agent_id), which may confuse.

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 clearly states the tool manages multi-agent crews with actions like CRUD and execution. It distinguishes the tool by focusing on crew coordination, but does not explicitly differentiate from sibling tools like team_manage or agent_manage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides guidance on async execution and polling, and mentions that agents must be real IDs. However, it lacks explicit when-to-use or when-not-to-use compared to alternatives. It implies usage but does not give clear exclusions.

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/escapeboy/agent-fleet-o'

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