Skip to main content
Glama
DOC Model Safety Gate

DOC Model Safety Gate

by laceykes

publishReviewedRun

Publish a reviewed run live using the outputs a human accepted or edited, ensuring pending or rejected AI changes cannot be released.

Instructions

Publish a reviewed run: runs the workflow LIVE using the outputs a human accepted or edited in the Safety Gate. The API refuses a LIVE run when any AI output is still pending or rejected, so an unreviewed change cannot be published through this tool.

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": {
      "workflowId": "<workflowId>",
      "reviewRunId": "<reviewRunId>"
    },
    "name": "publishReviewedRun"
  }
}

Input Schema

NameRequiredDescriptionDefault
workflowIdYesWorkflow ID
reviewRunIdYesID of the run whose outputs were reviewed in the Safety Gate

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses that this triggers a LIVE execution with real side effects, requires human-accepted inputs, and will fail hard on unreviewed changes. It does not mention permissions, whether the live run can be undone (rollbackRun exists as a sibling), or what is returned.

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 tight sentences with no filler; the action and its data source come first, followed by the safety constraint. Nothing is repeated and nothing is wasted.

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 two-parameter mutation tool with no annotations and no output schema, the description covers the essential trigger, inputs source, and failure mode. The main omission is what a successful call returns (run ID, status), which matters slightly more given there is no output schema.

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%, so both parameters are already documented in the schema. The description reinforces that reviewRunId refers to the human-reviewed run in the Safety Gate but adds no format, sourcing, or constraint detail beyond that. Baseline 3 applies.

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?

States a specific verb and resource ('Publish a reviewed run') and explains the mechanism: it runs the workflow LIVE using outputs a human accepted or edited in the Safety Gate. That is clearly distinct from a plain run or a rollback in substance, but the description never names a sibling (e.g. runWorkflow) to make the contrast explicit.

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 a clear precondition for use: only after a human has accepted or edited outputs in the Safety Gate. It also states the blocking condition (the API refuses a LIVE run when any output is pending or rejected). It stops short of naming which alternative to use when the run is not yet reviewed.

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