ReplyOnTheFly

Write a review reply

write_review_reply

Read-only

Writes a reply a business owner can post under a customer review on Google, Yelp, Facebook, TripAdvisor or Trustpilot. Use it when someone shares a review of their business and wants a response to it, including angry or negative reviews. The reply follows the star rating: it thanks happy customers, and for low ratings it acknowledges the problem without arguing and offers to make it right. It does not post anything anywhere; the owner copies the reply and posts it themselves. It does not write reviews.

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": {
      "business_name": "<business_name>",
      "star_rating": "<star_rating>"
    },
    "name": "write_review_reply"
  }
}

Input Schema

Name	Required	Description
`tone`	No	Voice of the reply. Defaults to friendly.
`length`	No	concise is 1 to 2 sentences, standard 2 to 3, detailed 3 to 4. Defaults to standard.
`platform`	No	Where the review was posted. Defaults to google.
`alternate`	No	Set true to get a differently worded version of a reply already written for the same review.
`owner_notes`	No	Facts or wishes the owner gave for this reply, e.g. "we fixed the AC last week" or "sign off as Maria". Only include what the owner actually said.
`review_text`	No	The review exactly as the customer wrote it. Leave out for a rating with no text.
`star_rating`	Yes	Star rating the customer gave, 1 to 5.
`business_name`	Yes	Name of the business being reviewed.
`business_type`	No	What kind of business it is, e.g. "dentist", "pizza restaurant", "plumber".
`reviewer_name`	No	The reviewer's display name, if shown. Leave out if unknown; the reply will not invent one.

Output Schema

Name	Required	Description	Default
`reply`	Yes
`platform`	Yes
`star_rating`	Yes
`business_name`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description reinforces this with the important clarification that nothing is posted and the owner must copy and paste the reply. It also discloses rating-dependent content behavior (thanks happy customers; acknowledges problems without arguing for low ratings), which is real context beyond the annotations. It doesn't address the 'alternate' regeneration behavior or idempotency, which keeps it from 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?

Opens with the core action, then layers usage, content behavior, and scope exclusions in about five tight sentences. No filler, and the most important constraint (nothing is posted) is given early enough to prevent misuse.

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 10-parameter generation tool with an output schema and full schema coverage, the description covers purpose, when to use, platform scope, rating-driven behavior, and the non-posting constraint. The one notable gap is that it never mentions the 'alternate' parameter's regeneration purpose, relying entirely on the 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 description coverage is 100%, so every parameter is already documented in the schema, including the tone/length/platform enums and the alternate flag. The description adds only indirect meaning, such as star rating shaping the reply's structure, and does not clarify the tone, length, or alternate parameters beyond what the schema says.

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?

States a specific verb and resource ('Writes a reply ... under a customer review') and names the five supported platforms. It also explicitly bounds scope with 'It does not post anything anywhere' and 'It does not write reviews,' which cleanly separates it from the sibling write_review_request_message.

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 trigger ('Use it when someone shares a review of their business and wants a response to it, including angry or negative reviews') plus a negative case ('does not write reviews'). It doesn't explicitly name the sibling tool or say when to use that one instead, so the routing is implied rather than stated.

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

All ReplyOnTheFly tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.