Skip to main content
Glama

review_workflow_draft

Approve (send, optionally with edited text) or discard a pending AI-drafted workflow message (confirm-gated). Sending reaches the client immediately, so only approve after the coach has seen the final text.

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": {
      "runId": "<runId>",
      "decision": "<decision>"
    },
    "name": "review_workflow_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNo
runIdYes
confirmNoMust be true to actually execute. If false/omitted, returns a preview only.
decisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

The annotations only say readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the description carries the important disclosure that sending reaches the client immediately and is effectively irreversible from the recipient's side, plus that the call is confirm-gated. It omits whether discarding permanently destroys the draft, which is the one remaining behavior an agent would want to know and which sits in mild tension with 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.

Conciseness5/5

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

Two sentences, front-loaded with the action and the option, then the safety constraint. Nothing is redundant with the schema and no sentence could be dropped without losing routing or safety information.

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 four-parameter, non-open-world mutation with no output schema, the definition covers the action, the optional edit, the confirmation gate, and the client-facing consequence. The gaps are the meaning of `runId` and what a discard returns or destroys.

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 description coverage is only 25% (only `confirm` is documented inline), so the description must compensate, and it does reasonably well: it explains that `text` is an optional edit applied at send time and that `decision` selects approve versus discard. `runId` is left unexplained, and the schema's own preview-only behavior for `confirm=false` is not reinforced in the description.

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 pairs the concrete verbs 'approve (send)' and 'discard' with a precisely qualified resource, a 'pending AI-drafted workflow message', and clarifies that approval can carry an edited `text`. That is enough to distinguish it from draft-listing siblings, but it never names or contrasts the nearby `approve_ai_run`, so the boundary between the two approval tools must still be inferred.

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 a real precondition for the risky branch ('only approve after the coach has seen the final text') rather than a generic 'use this to approve'. It does not state when discard is preferred over approve, nor does it route to siblings such as `list_ai_runs_awaiting_review` or `approve_ai_run`.

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.