Skip to main content
Glama

List reviews

list_reviews
Read-only

Reviews, newest first, in the same format for every platform. Filter by location(s), platform, dates, stars, a text search or whether they have a reply; filters combine. Use next_cursor for the next page. Each review carries its location_name and location_url; with q, matched_terms lists the names it matched. meta.pending_locations lists locations whose reviews haven't loaded yet (sync_status queued, importing, waiting_for_reads or error): say they are loading, not that they have no reviews. Example, reviews of the Seattle office that mention John: find its id with list_locations, then location_id="loc_abc", q="John,Johnny".

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_reviews"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoSearch the review text and title for whole words, ignoring case and accents. Separate up to 10 terms with commas to match any of them (OR): "John,Johnny". A term with spaces is a phrase ("John Smith"). "Ann" does not match "Annual".
q_inNoWhere q looks, comma separated: text, title, author. Default: text,title. Add author to find reviews written by someone named like q.
limitNoPage size. 20 here (the REST API defaults to 50).
sinceNoOnly reviews created on or after this date.
untilNoOnly reviews created on or before this date (a date covers that whole day, UTC).
cursorNonext_cursor from the previous page.
platformNo
has_replyNotrue: reviews with a reply in any status (a failed one included); false: reviews with no reply at all. For reviews that still need an answer use reply_status "none,failed".
max_ratingNoOnly reviews with at most this many stars.
min_ratingNoOnly reviews with at least this many stars (reviews with no stars are left out).
location_idNoOnly this location (from list_locations), or several ids separated by commas (up to 500): loc_a,loc_b.
reply_statusNoComma separated, any of: none, queued, published, failed, unknown. "none,failed" = still needs an answer.
ingested_sinceNoOnly reviews Prisma stored on or after this time, whenever they were written: to poll for new ones without missing a late import (a newly connected office’s history).
include_deletedNotrue: also reviews Prisma found removed from the platform (they carry deleted_at).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • changedInput schema / properties / has_reply / description
      Previous value: -"true: only answered reviews; false: only unanswered ones."New value: +"true: reviews with a reply in any status (a failed one included); false: reviews with no reply at all. For reviews that still need an answer use reply_status \"none,failed\"."
    • addedInput schema / properties / ingested_since
      Added value: +{
      +  "description": "Only reviews Prisma stored on or after this time, whenever they were written: to poll for new ones without missing a late import (a newly connected office’s history).",
      +  "type": "string"
      +}
    • addedInput schema / properties / limit / description
      Added value: +"Page size. 20 here (the REST API defaults to 50)."
    • changedInput schema / properties / location_id / description
      Previous value: -"Only this location (from list_locations)."New value: +"Only this location (from list_locations), or several ids separated by commas (up to 500): loc_a,loc_b."
    • addedInput schema / properties / max_rating
      Added value: +{
      +  "description": "Only reviews with at most this many stars.",
      +  "maximum": 5,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / min_rating
      Added value: +{
      +  "description": "Only reviews with at least this many stars (reviews with no stars are left out).",
      +  "maximum": 5,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / q
      Added value: +{
      +  "description": "Search the review text and title for whole words, ignoring case and accents. Separate up to 10 terms with commas to match any of them (OR): \"John,Johnny\". A term with spaces is a phrase (\"John Smith\"). \"Ann\" does not match \"Annual\".",
      +  "type": "string"
      +}
    • addedInput schema / properties / q_in
      Added value: +{
      +  "description": "Where q looks, comma separated: text, title, author. Default: text,title. Add author to find reviews written by someone named like q.",
      +  "type": "string"
      +}
    • addedInput schema / properties / reply_status
      Added value: +{
      +  "description": "Comma separated, any of: none, queued, published, failed, unknown. \"none,failed\" = still needs an answer.",
      +  "type": "string"
      +}
    • addedInput schema / properties / until
      Added value: +{
      +  "description": "Only reviews created on or before this date (a date covers that whole day, UTC).",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only declare a safe read, but the description adds substantial behavioral detail: next_cursor pagination, per-review location_name/location_url, matched_terms when q is used, and meta.pending_locations with the specific sync_status values that mean data is still loading. The warning to say 'loading' rather than 'no reviews' is exactly the kind of trap-avoidance an agent cannot get from structured fields.

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?

Ordering and format guarantees are front-loaded, followed by filters, pagination, return-shape notes, and one concrete example. Dense but every sentence carries operational value; the example is long but justified for a 14-parameter tool.

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?

With 14 optional parameters and no output schema, the description responsibly covers return shape (location_name, location_url, matched_terms, meta.pending_locations) and pagination. Remaining gaps are small, such as default date semantics for since/until and whether the 'newest first' order can be changed.

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 93%, so nearly every parameter is already documented in detail, including q, q_in, limit, has_reply and location_id. The description mainly restates that filters combine and repeats the q example already present in the schema. It adds marginal meaning beyond the schema, consistent with the baseline 3.

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 opening sentence names the resource (reviews) and its ordering (newest first) plus a normalization guarantee across platforms, which is real differentiating information. The enumeration of filter dimensions makes the tool's scope unambiguous. It stops short of 5 because the sibling list_deleted_reviews is never mentioned, even though include_deleted overlaps with it.

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 explicit operating guidance: filters combine, use next_cursor for pagination, and a worked example chaining list_locations to obtain a location_id before calling this tool. It also instructs how to report pending_locations rather than misreporting missing reviews. No exclusion tells the agent when to prefer get_review or list_deleted_reviews instead.

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