Walmart & Amazon review insights: complaints, topic sentiment, new-review alerts. Pay per result.
Scored across 3 tools
The Amazon vs. Walmart split is clear from the prefixes, so amazon_reviews and walmart_reviews are easy to tell apart. However, walmart_product and walmart_reviews overlap: both return product details and review topics, so an agent choosing a tool for a Walmart item faces a real boundary question.
All three tools follow the same {platform}_{resource} snake_case pattern: amazon_reviews, walmart_product, walmart_reviews. No mixed conventions or vague verbs.
Three tools is thin for a multi-retailer reviews server, and the surface is asymmetric: Walmart gets both a product tool and a reviews tool, while Amazon gets only a reviews tool. If the scope really is reviews data, three is defensible but feels under-built.
There is no Amazon product-details counterpart to walmart_product, so Amazon pricing/rating context is only reachable indirectly through review metadata. Keyword or category search, and any retailer beyond Amazon/Walmart, are absent, leaving notable gaps for a 'reviews' domain.
Amazon top reviews merged across marketplaces, plus Amazon's "Customers say" topics with sentiment.
product: ASIN or Amazon product URL (e.g. "B00FLYWNYQ").
marketplaces: comma list such as "US,CA,UK" (each adds its own ~8-13 top reviews; max 5).
| Name | Required | Description | Default |
|---|---|---|---|
| stars | No | ||
| product | Yes | ||
| marketplaces | No | US | |
| verified_only | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint and idempotentHint, so the safety profile is covered externally. The description adds genuinely useful behavioral context beyond that: each marketplace contributes roughly 8-13 top reviews and up to 5 marketplaces can be merged, which sets result-volume expectations.
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 purpose sentence is front-loaded and the parameter notes are terse and example-driven with no filler. Slightly fragmented formatting (trailing blank line, sentence fragment style) keeps it from a 5, but every sentence earns its place.
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?
With four parameters, no output schema and no enum guidance, the description leaves meaningful gaps: the `stars` filter format and `verified_only` behavior are unaddressed, and return-shape expectations (per-marketplace review lists plus topic sentiments) are only gestured at. What it covers it covers well, but it is not complete for this parameter set.
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 0%, so the description carries the full burden, and it only documents two of four parameters. It does add real value for those two (ASIN-or-URL format with an example for product; comma-list syntax and a per-marketplace review estimate for marketplaces), but `stars` and `verified_only` are left completely unexplained, including the ambiguous string format of `stars`.
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 states a specific resource and behavior: Amazon top reviews merged across marketplaces, plus "Customers say" topics with sentiment. That is far more specific than the name alone. It differentiates itself from the walmart_* siblings implicitly through the Amazon scope, but never names them, so it stops short of a 5.
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?
Usage is implied by the platform scope (Amazon reviews vs walmart_reviews), but there is no explicit when-to-use or when-not-to-use guidance, and no stated prerequisites or alternative selection logic. An agent can infer the intent, but the description does not route it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Walmart product details: price, stock, seller, category, rating breakdown and review topics.
product: Walmart item ID or product URL.
| Name | Required | Description | Default |
|---|---|---|---|
| product | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is covered. The description adds the returned data fields, but discloses nothing about rate limits, auth needs, or pagination for this external data source.
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 tight lines: purpose/return payload first, parameter semantics second. No filler and everything is front-loaded.
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?
For a single-parameter read tool with no output schema, the description covers purpose, return fields and the parameter format, and annotations handle safety. Only usage routing to the review siblings is absent.
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 coverage is 0%, so the description must carry the parameter, and it does: 'product: Walmart item ID or product URL.' It tells the agent the two accepted input formats, which meaningfully compensates for the undocumented schema field.
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?
Names a specific resource (Walmart product details) and enumerates exactly what it returns – price, stock, seller, category, rating breakdown and review topics. This makes it distinguishable from walmart_reviews, though the sibling is not named explicitly.
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?
There is no when-to-use guidance and no alternative named. The mention of 'review topics' sits adjacent to the walmart_reviews sibling but the description never tells the agent to prefer that tool for review-only queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Walmart reviews for one product, with filters.
product: Walmart item ID or product URL (e.g. "10450114").
max_reviews: 1-200. stars: comma list like "1,2" for complaints.
verified_only: verified purchases only. topic: Walmart review topic such as "Freshness".
since: only reviews on/after YYYY-MM-DD. Returns product details, reviews (with topic
sentiment) and a summary of reviews available vs delivered.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | ||
| stars | No | ||
| topic | No | ||
| product | Yes | ||
| max_reviews | No | ||
| verified_only | No | ||
| include_product | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent and open-world behavior, so the safety profile is covered. The description adds genuine non-annotation value by disclosing the return shape (product details, reviews with topic sentiment, and a summary of reviews available vs. delivered), which is important given there is no output schema.
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?
One summary sentence followed by a tight per-parameter list; the purpose is front-loaded and every line earns its place. Scannable and free of 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?
With no output schema the description correctly compensates by describing returns, and it documents nearly all seven parameters. The undocumented include_product flag and lack of any pagination or rate-limit note are the only remaining gaps for a complex, filter-heavy read tool.
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 0%, so the description carries the full burden and mostly succeeds: it documents product (ID or URL with example), max_reviews range 1-200, stars comma syntax, verified_only, topic format, and since date format. Only include_product is left undocumented, a small gap in otherwise strong parameter coverage.
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 opening sentence states a specific resource (Walmart reviews for a single product) and notes filtering, which cleanly separates it from amazon_reviews by retailer. It is clear enough to select the right tool, though it never explicitly contrasts itself with the sibling walmart_product even though it also claims to return product details.
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?
There is no when-to-use or when-not guidance; the agent must infer the scenario from the tool name alone. The overlap with walmart_product is left unresolved, since the description advertises 'product details' without saying when the dedicated product tool should be preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
amazon_reviewswalmart_productwalmart_reviewsWalmart search, product pages and customer reviews on walmart.com and walmart.ca, as JSON.
Analyze product reviews: pain points, feature requests, sentiment and competitive gaps for sellers.
Customer-voice research: scrape reviews and comments from 30+ sites, find ads, hooks, creators.
Sentiment, complaint themes, quotes, business reports and reply drafts for any reviews dataset.
Add one secure layer between your agents and this server.
