Skip to main content
Glama

Approve Automation Proposal

approveAutomationProposal

Approve the automation proposal of a Module automation being set up, the same as the setup's Approve and build in the web app: it opens an Ask Duvo conversation that reads the proposal and the Policy, proposes which Agents, Queues and dashboards change, makes the changes once the user agrees there, and finishes the setup. Give the user the conversation's url; they answer Duvo's plan in it. proposal_snapshot_id, when given, must be the live proposal. A build already started is returned with status already_started rather than started twice. Refused with 409 when there is no live proposal, required Policy questions are open, or Ask Duvo isn't available to the team, and with 403 below Builder. With Automation conversion in Ask Duvo on for the team, the conversation runs the same build specification flow as Clarity's Create automation against this automation, and takes its access too: 403 unless the caller created the process, is a Lead Builder or above, or the team's Clarity access is unrestricted. Confirm with the user before calling: approving starts the build.

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": {
      "automation_id": "<automation_id>"
    },
    "name": "approveAutomationProposal"
  }
}

Input Schema

NameRequiredDescriptionDefault
automation_idYesAutomation ID
proposal_snapshot_idNoThe automation proposal being approved. Must be the live proposal; leave out to approve whichever proposal is live.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well past the annotations: it explains that approval opens an Ask Duvo conversation, that the user answers in that conversation, that the caller should surface the conversation `url`, that an in-flight build returns `already_started`, and it enumerates 409 and 403 conditions plus Builder-level and Clarity access requirements. The annotations only flag non-read-only, non-destructive, non-open-world, non-idempotent; the description supplies the actual consequence, failure modes, and auth gates.

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?

Purpose and the critical 'confirm with the user' warning are front-loaded, and the dense sentences each carry real information (conversation behavior, error codes, permission tiers). It is longer than ideal for a two-parameter tool and packs several clauses into single run-on sentences, but there is little outright filler.

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?

For a mutating, permission-gated tool with no output schema, the description covers the side effects, the returned conversation URL and `already_started` status, the refusal codes, and the layered authorization rules. An agent has enough to decide, confirm, and interpret the outcome without further documentation.

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 schema descriptions already state that `proposal_snapshot_id` must be the live proposal and may be omitted to approve whichever is live. The description's 'must be the live proposal' clause largely restates the schema rather than adding format, sourcing, or retrieval guidance (e.g., where to obtain the snapshot id).

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?

States a specific verb and resource ('Approve the automation proposal of a Module automation being set up') and anchors it to a known UI action ('the same as the setup's Approve and build'). It is clearly distinguishable from generateAutomationProposal (creates the proposal) and buildClarityAutomation (different product surface), both of which appear among siblings.

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 concrete preconditions ('must be the live proposal', 'Confirm with the user before calling: approving starts the build') and implicitly routes agents to generate a proposal first by stating a 409 when no live proposal exists. It does not explicitly name the alternative tool to call when no live proposal exists, so it stops short of full when/when-not routing.

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