Generate 2-3 reply drafts for one review using ReputeMap's tuned generator (the same one the app uses, with the business's saved voice and sign-off), and save the draft so it appears in the app's editor. NEVER publishes anything - drafts only.
| Name | Required | Description | Default |
|---|---|---|---|
| review_id | Yes | UUID from list_reviews | |
| instructions | No | optional one-off guidance for this draft, e.g. 'mention the new units' or 'keep it under 40 words' |
Changes observed during successful MCP inspections.
Input schema / properties / instructionsAdded value: +{
+ "description": "optional one-off guidance for this draft, e.g. 'mention the new units' or 'keep it under 40 words'",
+ "maxLength": 300,
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already set readOnlyHint=false and idempotentHint=false, so write behavior is partially declared. The description adds real value beyond them: drafts use the business's saved voice/sign-off, get persisted into the app editor, and never publish. It does not address repeat-invocation behavior or whether drafts overwrite previous ones.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two dense sentences with the non-publishing guarantee front-loaded in a memorable caps phrase. No filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, yet 'generate 2-3 reply drafts' gives a usable sense of the return. Coverage of persistence and scope is strong; only the exact response shape and repeat-call behavior remain unspecified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (review_id sourced from list_reviews, instructions as optional one-off guidance), so the schema carries the parameter load. The description adds only that generation is tuned by saved voice and sign-off, which is not parameter-level detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource: generate 2-3 reply drafts for one review and save it so it appears in the editor. The 'NEVER publishes anything - drafts only' line cleanly separates it from the sibling publish_reply.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Makes clear when this tool applies (generating drafts, not publishing) and implicitly points to publish_reply as the separate step. It lacks an explicit 'use publish_reply to send' signpost, so it stops short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.