Skip to main content
Glama
DOC Model Safety Gate

DOC Model Safety Gate

by laceykes

reviewOutput

Record a human review decision (accepted, rejected, or edited) for an AI output, supplying the corrected value when edited, so a run can go LIVE only after every output is reviewed.

Instructions

Record a human review decision for one AI output in the Safety Gate: accepted, rejected, or edited. When the action is edited, pass editedValue with the corrected value. Reviewing never publishes anything by itself; a run can only go LIVE after every output is reviewed.

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": {
      "id": "<id>",
      "action": "<action>"
    },
    "name": "reviewOutput"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesAI output ID
actionYesReview decision
editedValueNoCorrected value, required when action is edited

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.2/5.0
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 meaningful work: it discloses that this is a mutation ('Record a review decision'), that it has no publish side effect ('Reviewing never publishes anything by itself'), and the gate condition required to reach LIVE. It does not cover whether an existing review can be overwritten, whether reviews are idempotent, or any permission requirements, which keeps it below a 5.

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?

Three short sentences, front-loaded with the core action, followed by the conditional parameter rule and then the side-effect constraint. No sentence is redundant and nothing is buried.

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 three-parameter mutation tool with no annotations and no output schema, the description covers purpose, the conditional parameter, and the key side-effect boundary. It could say more about what a review call returns or how to revise an existing review, but nothing essential to invoking it correctly is missing.

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 description coverage is 100%, so all three parameters are already documented, including the conditional requirement on editedValue. The description restates that condition without adding format, validation, or edge-case detail beyond the schema, so the baseline of 3 applies.

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 opens with a specific verb and resource ('Record a human review decision for one AI output') and constrains scope to a single output, which implicitly contrasts with the bulk-review sibling. It also enumerates the three decision values, so an agent knows exactly what this tool produces without opening the schema.

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 clear conditional rule: when action is 'edited', pass editedValue. It also states a workflow-level constraint (a run can only go LIVE after every output is reviewed), which tells the agent this tool is a prerequisite step. It stops short of explicitly naming bulkReviewOutputs as the alternative for multi-output review, so guidance is strong but not fully exhaustive.

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