Skip to main content
Glama

Draft Review Reply Tool

draft-review-reply
Read-only

Drafts a policy-aware reply for one authorized review without posting or changing the review. Use to draft review reply in the connected business. Returns review, suggestion, tone, policy_mode, policy_decision, risk_analytics, persisted, posted, scope.

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": {
      "review_id": "<review_id>"
    },
    "name": "draft-review-reply"
  }
}

Input Schema

NameRequiredDescriptionDefault
toneNoDraft tone.
review_idYesReview ID returned by search-reviews.

Output Schema

NameRequiredDescriptionDefault
toneYesTone used or returned by this tool.
scopeYesAuthorization scope of this result; data remains restricted to the connected business.
postedYesPosted flag; previews do not perform this action.
reviewYesReview data returned by the authorized safe projection.
persistedYesPersisted flag; previews do not perform this action.
suggestionYesSuggestion used or returned by this tool.
policy_modeYesPolicy mode used or returned by this tool.
risk_analyticsYesRisk analytics metadata; empty collections retain their existing JSON array representation.
policy_decisionYesPolicy decision metadata; empty collections retain their existing JSON array representation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / required
      Added value: +[
      +  "review_id"
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "persisted": {
      +      "description": "Persisted flag; previews do not perform this action.",
      +      "enum": [
      +        false
      +      ],
      +      "type": "boolean"
      +    },
      +    "policy_decision": {
      +      "description": "Policy decision metadata; empty collections retain their existing JSON array representation.",
      +      "type": [
      +        "object",
      +        "array",
      +        "null"
      +      ]
      +    },
      +    "policy_mode": {
      +      "description": "Policy mode used or returned by this tool.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "posted": {
      +      "description": "Posted flag; previews do not perform this action.",
      +      "enum": [
      +        false
      +      ],
      +      "type": "boolean"
      +    },
      +    "review": {
      +      "description": "Review data returned by the authorized safe projection.",
      +      "type": "object"
      +    },
      +    "risk_analytics": {
      +      "description": "Risk analytics metadata; empty collections retain their existing JSON array representation.",
      +      "type": [
      +        "object",
      +        "array",
      +        "null"
      +      ]
      +    },
      +    "scope": {
      +      "description": "Authorization scope of this result; data remains restricted to the connected business.",
      +      "enum": [
      +        "connection_business"
      +      ],
      +      "type": "string"
      +    },
      +    "suggestion": {
      +      "description": "Suggestion used or returned by this tool.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "tone": {
      +      "description": "Tone used or returned by this tool.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    }
      +  },
      +  "required": [
      +    "review",
      +    "suggestion",
      +    "tone",
      +    "policy_mode",
      +    "policy_decision",
      +    "risk_analytics",
      +    "persisted",
      +    "posted",
      +    "scope"
      +  ],
      +  "type": "object"
      +}
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's 'without posting or changing the review' reinforces rather than carries that burden. It does add genuine context beyond annotations: the reply is 'policy-aware', and results include policy_mode, policy_decision, risk_analytics, persisted, and posted, which tells the agent a draft may be persisted and evaluated without being published. It stops short of explaining what a policy_decision outcome means or how risk_analytics should be interpreted.

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?

The core statement is front-loaded and efficient, and the non-mutation constraint lands immediately. However, the second sentence restates the purpose redundantly, and the trailing comma-separated return-field list duplicates the output schema and adds bulk without value.

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?

This is a simple two-parameter tool with an output schema, and the description covers the key facts an agent needs: one review, authorization required, no posting or mutation, and policy/risk evaluation in the result. The main gap is that the enumerated return fields duplicate the output schema instead of explaining how to act on a policy decision.

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 review_id and the tone enum are already fully documented in the schema. The description mentions 'tone' only as part of a return-field list and adds no syntax, defaults, or format guidance beyond what the schema provides. Baseline 3 is appropriate.

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 first sentence names a specific verb and resource ('Drafts a policy-aware reply') and pins the scope to 'one authorized review' while explicitly excluding posting or mutation. That is clear enough to distinguish it from a publish/reply action, though it never names a sibling tool. The follow-up sentence 'Use to draft review reply in the connected business' adds nothing.

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?

Usage is only implied: the description says to use it to draft a reply and that it will not post or change the review. There is no explicit when-to-use versus an alternative (e.g., a preview or post tool), and no stated prerequisites such as authorization or review ownership beyond the word 'authorized'.

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