Skip to main content
Glama

WB Reviews by imt_id

wb_reviews
Read-onlyIdempotent

Fetches Wildberries reviews by imt_id across product variants and sorts them to surface lowest-rated complaints; an empty pool means no reviews, not an error.

Instructions

Fetch reviews by imt_id (root_id from wb_root_info).

All product variants share one review pool, indexed by imt_id NOT nmId.

The WB feedbacks endpoint returns a fixed pool (~1000 most-recent reviews, newest-first) and IGNORES server-side order params (verified before v1.0.0, July 2026), so sort is applied CLIENT-SIDE over that pool. To surface complaints, "worst" reorders the returned pool by lowest rating first.

an empty pool is NOT an error — a healthy response with zero feedbacks.

Full field list and error codes: guide://wb/wb_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": {
      "imt_id": "<imt_id>"
    },
    "name": "wb_reviews"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo"recent"/"newest"/"default" (as returned, newest-first), "best"/"highest" (highest rating first), "worst"/"lowest"/"complaints" (LOWEST rating first — finds downsides). Reorders the ~1000-review pool WB returns, not all feedbacks.recent
limitNoMax review texts to return (1..100). Counts always full.
imt_idYesRoot ID (imt_id) from wb_root_info. All product variants share one review pool indexed by imt_id, NOT by nmId.

Output Schema

NameRequiredDescriptionDefault
metaNo
sortNo
imt_idNo
feedbacksNo
host_usedNo
pool_sizeNo
valuationNo
feedback_countNo
valuation_distributionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.5.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only state readOnly/idempotent/openWorld; the description adds the operationally decisive facts an agent cannot infer: the endpoint returns a fixed ~1000-review newest-first pool, ignores server-side order params, and therefore sort is applied client-side. It also preempts a false failure mode by declaring that an empty pool is a healthy zero-result response, not an error.

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?

Front-loaded with the resource and identifier, then layers the pool caveat and the sort consequence — no filler sentences. Minor deduction for the '(verified before v1.0.0, July 2026)' parenthetical, which is provenance flavor rather than something an agent needs to act.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter tool whose annotations already cover the safety profile and which has an output schema, nothing call-critical is missing: identifier source, pool limitation, sort semantics, limit semantics, and empty-result behavior are all stated. It also delegates field lists and error codes to guide://wb/wb_reviews rather than bloating the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description earns above that by explaining that sort reorders only the returned pool rather than the full feedback set, and that limit caps review texts while counts remain full. That is genuine meaning beyond the schema's enum-free string values.

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?

Opens with a specific verb+resource ('Fetch reviews by imt_id') and immediately pins the identifier semantics: imt_id is the root_id from wb_root_info, and the review pool is indexed by imt_id NOT nmId. That nmId exclusion is exactly the distinction an agent needs to avoid calling card-style siblings with the wrong key.

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 concrete conditional guidance — use sort='worst' when the goal is to surface complaints — plus the crucial caveat that sorting is client-side over a fixed pool, so 'worst' is not the worst of all feedbacks. It does not explicitly contrast with siblings such as wb_questions (Q&A) or ozon_reviews (other marketplace), but the usage context is otherwise unambiguous.

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