Skip to main content
Glama

Workflow Manage Tool

workflow_manage
Destructive

Manage workflow template lifecycle: create, duplicate, validate, activate, and delete. Generate DAGs from natural language and estimate costs.

Instructions

Workflow templates — reusable DAGs that experiments and project runs execute. This tool covers metadata and lifecycle; for graph editing use workflow_graph. Lifecycle states: draft → active → archived. Activation is gated on validate passing.

Core actions:

  • list / get (read) — optional: status filter.

  • create (write) — name, description.

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

  • delete (DESTRUCTIVE) — workflow_id. Soft-deletes; running experiments continue on cached graph.

  • validate (read) — workflow_id. Returns errors[] (cycles, orphans, invalid types) and warnings[].

  • activate (write) — workflow_id. Requires validation to pass.

  • duplicate (write) — workflow_id. Creates a draft copy with the same graph.

AI / cost:

  • generate (write — costs LLM credits) — prompt. Decomposes natural language into a workflow graph and saves as draft.

  • estimate_cost (read) — workflow_id. Projected per-run credit cost.

  • suggestion (read — costs LLM credits) — context (object). Recommends improvements.

Advanced:

  • time_gate (write) — workflow_id, config (delay/window). Adds time-based gating around step execution.

  • execution_chain (write) — workflow_id, chain config. Configures sequential workflow chaining.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: list, get, create, update, validate, activate, duplicate, generate, estimate_cost, suggestion, time_gate, execution_chain
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)
workflow_idYesThe workflow UUID
nameYesWorkflow name
descriptionNoWorkflow description
checkpoint_modeNoCheckpoint durability mode: sync (safest, DB write per step), async (Redis buffer + background flush), exit (in-memory, flushed on completion). Default: sync
budget_cap_creditsNoMaximum credits this workflow may consume per execution. Propagated to each experiment created from this workflow. Omit for no cap.
observability_configNoObservability provider config. Schema: {"provider":"langfuse|langsmith|none","enabled":true,"config":{"public_key":"...","secret_key":"...","host":"https://cloud.langfuse.com"}}
titleNoName for the new workflow (defaults to "<original name> (copy)")
promptYesNatural language description of the workflow to create
experiment_idYesID of the completed or evaluating workflow experiment to analyze.
event_typeNoFilter by event type: started, completed, failed, waiting_time, waiting_human, skipped
Behavior5/5

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

The description adds significant behavioral context beyond annotations: delete is soft-delete, generate and suggestion incur LLM credits, activation requires validation, time_gate and execution_chain add advanced behavior. It does not contradict the destructiveHint annotation.

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 long but well-structured with sections for core actions, AI/cost, and advanced. It front-loads the purpose and uses bullet points, making it scannable despite length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (12 actions, 14 params, no output schema), the description covers all actions, lifecycle states, cost implications, and edge cases like soft-delete and validation gating. It is comprehensive.

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 100%, so baseline is 3. The description adds value by grouping parameters with actions (e.g., 'create (write) — name, description'), which provides context beyond individual schema descriptions.

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 clearly states the tool covers workflow template metadata and lifecycle, and distinguishes from the sibling tool workflow_graph for graph editing. It lists specific actions with their purposes, making the scope well-defined.

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?

The description provides explicit context for when to use certain actions (e.g., graph editing via workflow_graph, lifecycle states, activation gated on validation). It lacks explicit exclusions for other sibling tools but is otherwise clear.

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