List Google reviews for the org (newest first) with the published reply text inlined. Filter by location, star-rating range, replied/unreplied, or a trailing day window.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No | ||
| rating_max | No | ||
| rating_min | No | ||
| since_days | No | only reviews from the last N days | |
| location_id | No | UUID from list_locations; omit for all locations | |
| unanswered_only | No | true = only reviews without an owner reply |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate a safe read operation (readOnlyHint, idempotentHint). The description adds value by revealing ordering, inclusion of reply text, and filter capabilities, which are behavioral details not present in annotations.
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?
The description is two sentences, front-loaded with the main purpose, and every word adds value. There is no superfluous information.
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?
The description covers ordering, reply text, and filters, but omits pagination details (limit/offset, default limit, maximum results) and does not specify the full return structure in the absence of an output schema. Adequate but with gaps.
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 43%, so the description partially compensates by grouping filter categories (location, star-rating, replied/unreplied, trailing days). However, it does not add details for limit, offset, or rating_min/max beyond what the schema provides, missing an opportunity to clarify default behavior.
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?
The description clearly states the action ('List'), the resource ('Google reviews for the org'), ordering ('newest first'), and includes that reply text is inlined. It also lists filtering options, distinguishing it from siblings like get_review_stats or list_locations.
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?
The description implies the tool is for listing reviews with various filters, providing clear context. However, it does not explicitly state when to use alternatives like get_review_stats or when not to use this tool, so it lacks explicit exclusions.
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.
Each tool targets a distinct action or resource: listing locations, listing reviews, aggregated stats, drafting vs. publishing replies, review requests, and usage tracking. The two reply tools are clearly separated by internal vs. public visibility.
All tools follow a consistent verb_noun pattern (list, get, draft, publish, send) with clear, descriptive nouns. No mixed conventions or vague verbs.
Seven tools provide a focused but complete set for the core reputation management workflows. Each tool serves a distinct purpose without redundancy or bloat.
Covers the main lifecycle: list locations/reviews, draft and publish replies, send review requests, and view stats. Minor gaps like direct editing of existing drafts or reply history are possible but not critical for core functionality.
