Skip to main content
Glama
DOC Model Safety Gate

DOC Model Safety Gate

by laceykes

listPendingReviews

Lists workflow runs with AI outputs awaiting human review in the Safety Gate and shows a pending count for each, so you can identify unpublished changes needing approval.

Instructions

List workflow runs whose AI outputs are waiting for human review in the Safety Gate, with a pending count for each. Nothing in these runs has been published.

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": {
      "projectId": "<projectId>"
    },
    "name": "listPendingReviews"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYesProject ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. "List" implies a read-only operation and the description usefully discloses state (unpublished, awaiting review) and that each result carries a pending count, but says nothing about permissions, pagination, or whether runs with zero pending items appear.

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 short sentences, zero filler. The scoping condition comes first and the publish-state clarification follows as a second, genuinely informative clause.

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 one-parameter read tool with no output schema, the definition is largely sufficient: it names the domain (Safety Gate), the filter (pending review), and the per-run return element (pending count). Minor gaps remain around result ordering and pagination for a potentially long run list.

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% for the single projectId parameter, so the schema already documents it fully; the description adds no format, scoping, or default detail beyond that. Baseline 3 applies when the schema does the heavy lifting.

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 ("List workflow runs") plus a precise filter: AI outputs awaiting human review in the Safety Gate, with a per-run pending count. That distinguishes it from action siblings like reviewOutput and bulkReviewOutputs, though no sibling is named explicitly.

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 conveys the situation that selects this tool (you want runs awaiting review), and the "Nothing in these runs has been published" line implies it is a pre-publish queue. It gives no explicit when-not guidance or named alternative such as getGateReview for inspecting a single item, so routing is inferred rather than stated.

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