Editorial picks for e-bikes, power stations, EV chargers, and robot vacuums, by use case and budget
Scored across 6 tools
Most tools are cleanly separated by resource and action: get_guide vs get_product_details vs list_buying_guides target clearly different artifacts. The one mild overlap is search_products versus recommend_product, since both surface products, but the descriptions differentiate browse/filter from reasoned recommendation.
All six tools follow a consistent verb_noun snake_case convention (compare_, get_, list_, recommend_, search_). The pattern is predictable and readable throughout.
Six tools is well-scoped for a product-recommendation and buying-guide site. Each tool maps to a distinct user need (search, compare, recommend, details, guides, browse) with no filler.
The read-only content surface is well covered: product search, head-to-head comparison, single-product details, recommendations, and both listing and full-text access to buying guides. No obvious dead ends for the stated purpose.
Head-to-head comparison of two or more products by slug.
| Name | Required | Description | Default |
|---|---|---|---|
| slugs | Yes | Product slugs to compare |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It does not state whether the operation is read-only, what the output format is, how errors (e.g., invalid slugs) are handled, or which product attributes are compared. This is a significant gap given the lack of structured metadata.
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 a single 8-word sentence that front-loads the action ('Head-to-head comparison') and specifies the resource. There is zero filler or redundancy; every word 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?
The tool lacks an output schema and has no annotations, so the description must convey what the comparison yields. It does not specify whether it compares prices, specifications, reviews, or how results are presented, leaving an agent unsure about the tool's output and whether it fits the user's intent. Essential context is missing.
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?
The schema fully describes the 'slugs' parameter (array of strings, minItems 2) with its own description. The tool description adds only 'by slug', which restates the parameter's role without providing additional meaning like examples, value constraints, or usage nuances. Per rubric, 100% schema coverage yields a baseline of 3, and no meaningful extra info is added.
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 a specific verb ('compare') and resource ('products') with a method ('by slug'). It differentiates from siblings like get_product_details (singular product details) and search_products (search) by emphasizing a head-to-head comparison of two or more products.
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 provides a clear context tied to comparing multiple products, which implies when to use it. However, it does not explicitly mention when not to use it or call out alternatives like get_product_details for a single product. The absence of exclusions keeps it at a 4 rather than a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full text of one buying guide by slug: the short answer, key takeaways, every section with its bullets, and the FAQ. Use this to answer 'how do I choose / what size / what should I look for' questions rather than only recommending a product.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Guide slug, e.g. what-size-portable-power-station |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It clearly discloses the operation's behavior: fetching the full text of a guide, including specific components. It does not cover failure modes or authentication, but for a simple single-slug retrieval tool the disclosed content is substantial.
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 with no filler. The return content is front-loaded, and the usage context follows immediately. Every clause 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?
For a one-parameter retrieval tool with no output schema, the description adequately explains what the tool returns and when to use it. Since there is no output schema, the detailed enumeration of return content is especially valuable and covers what an agent needs.
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 100%, and the schema already documents the slug parameter with an example. The description adds only the phrase 'by slug', which does not enhance the parameter's meaning beyond the schema. The baseline of 3 applies because the schema fully handles the single parameter.
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?
Description states a specific verb and resource: 'Full text of one buying guide by slug', and enumerates exactly what is included (short answer, key takeaways, sections, FAQ). It also differentiates itself from the recommend_product sibling by framing the tool as the answer source for how-to-choose questions.
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 second sentence gives explicit guidance on when to use this tool: for 'how do I choose / what size / what should I look for' questions, and contrasts it with recommending a product. It does not name alternative siblings like list_buying_guides or get_product_details, but the usage context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full editorial record for one product by slug: rating, pros/cons, specs, full review text, review URL, and buy link.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Product slug, e.g. aventon-aventure-3 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral burden. It clearly indicates a read-style retrieval and enumerates the returned content, but it does not disclose behavior for invalid or missing slugs, auth requirements, or error handling. Adequate but not richly transparent.
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 efficient sentence that front-loads the resource and identifier before listing the returned fields. Every clause adds informational value and there is no 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?
For a simple one-parameter retrieval tool with no output schema, the description is sufficient: it names the input and fully enumerates what will be returned. No critical element needed to call the tool correctly is missing.
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 100%: the slug parameter is described with an example ('aventon-aventure-3'). The description only repeats 'by slug' and adds no new format, constraints, or behavioral nuance beyond the schema.
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?
States a specific verb ('get'), resource ('product'), and selection method ('by slug'), then enumerates the returned components: rating, pros/cons, specs, full review text, review URL, and buy link. This clearly distinguishes it from siblings like search_products and compare_products.
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 only implied: 'for one product by slug' suggests the agent should use this when it already has a slug and needs the full editorial record. However, the description provides no explicit when-to-use guidance or comparison with alternatives such as search_products.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List everything we cover: product categories (with guide URLs, product counts and FAQs) plus our long-form buying guides, each with a one-sentence standalone answer and key takeaways.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden and does a good job by specifying the response structure: categories, FAQs, standalone answers, and key takeaways. 'List' signals a read-only operation, though it doesn't explicitly mention pagination, ordering, or potential payload size.
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?
A single sentence that is front-loaded with the action and then uses a colon to pack in precise return details without filler. Every phrase 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?
For a zero-parameter list tool with no output schema, the description covers return content well: categories, guide URLs, counts, FAQs, and guide-level answers/takeaways. It only omits minor operational details like ordering or pagination, which are unlikely to change the call.
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?
The tool has zero parameters and a 100%-covered empty schema, so the baseline is 4. The description adds meaning by clarifying what the returned list contains, which is more than the schema alone provides.
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 opens with the verb 'List' and a specific scope ('everything we cover'), then enumerates the exact content: product categories with guide URLs, counts, and FAQs, plus long-form buying guides with standalone answers and takeaways. This clearly distinguishes it from singular tools like get_guide and from search or comparison tools.
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 phrase 'List everything we cover' implies use when an agent needs a broad catalog overview, but it never explicitly says when to prefer this over get_guide, search_products, or compare_products. No exclusions or alternative routing are given, so usage is only 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.
Recommend the best product for a described use case and optional budget. Returns a top pick with reasoning plus alternatives.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Optional category slug to restrict to | |
| use_case | Yes | What the buyer needs, e.g. 'commuting 10 miles daily in a hilly city' or 'backup power for a fridge during outages' | |
| budget_usd | No | Optional budget in USD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states that the tool returns a top pick, includes reasoning, and provides alternatives. This gives an agent a solid understanding of the operation's behavior, though it does not describe edge cases like budget handling or output limits.
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 with no filler. It front-loads the purpose and follows with the output behavior, making it easy to parse quickly.
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 simple tool with three well-documented parameters and a verbally described output, the description covers the essential information. It could be slightly more complete by clarifying what kind of alternatives are returned or how choices are ranked, but nothing critical is missing for basic invocation.
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 100%, so the schema already documents all three parameters clearly. The description adds contextual meaning for 'use case' and 'budget' but does not add semantics beyond the schema for the 'category' parameter. Baseline 3 is appropriate.
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 uses a specific verb ('Recommend') and resource ('best product') and clearly defines the input conditions ('described use case and optional budget'). It also states the output format ('top pick with reasoning plus alternatives'), which distinguishes it from sibling tools like search_products or compare_products.
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 should be used when a buyer describes a use case and wants a curated recommendation, but it does not explicitly state when to prefer it over alternatives such as search_products, compare_products, or get_product_details. The usage context is clear but no exclusions or alternative routing are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search or browse our recommended products. Filter by category slug, maximum price, and/or a free-text query matched against name, brand, award, and use case.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Free-text search terms | |
| category | No | Category slug: electric-bikes | portable-power-stations | home-ev-chargers | robot-vacuums | cordless-drills | air-fryers | electric-lawn-mowers | |
| max_price_usd | No | Maximum approximate price in USD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral disclosure burden. It does not state whether the operation is read-only, how results are ordered, whether pagination exists, or whether an empty result set is possible — all important for a search tool with zero annotation coverage.
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 efficient sentences with no filler, front-loaded with the core action and immediately followed by filtering options. It could be tightened slightly but wastes nothing significant.
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 search tool with no annotations and no output schema, the description is minimal. It lacks usage routing relative to siblings and says nothing about result behavior (ordering, limits, empty results), leaving meaningful gaps for an agent to call it correctly.
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 100%, so the schema already documents all three parameters, including the category slug enum values. The description adds marginal value by noting the query is matched against name, brand, award, and use case — behavior beyond the schema — but this is a baseline-equivalent contribution given full schema 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 description states a clear verb ('search or browse') and resource ('recommended products'), and specifies the matching fields (name, brand, award, use case). However, it doesn't explicitly differentiate from siblings like recommend_product, which might also return recommended products, so it falls 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 'filter by category slug, maximum price, and/or a free-text query', suggesting this is the tool for filtered product discovery. But there is no explicit when-to-use guidance versus alternatives such as recommend_product or compare_products, leaving the agent to infer the fit.
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.
search_products1 field changedInput schema / properties / category / descriptionPrevious value: -"Category slug: electric-bikes | portable-power-stations | home-ev-chargers | robot-vacuums | cordless-drills"New value: +"Category slug: electric-bikes | portable-power-stations | home-ev-chargers | robot-vacuums | cordless-drills | air-fryers | electric-lawn-mowers"compare_productsget_guideget_product_detailslist_buying_guidesrecommend_productsearch_productsDescribe a problem in plain language; get matching products with honest caveats. Never sponsored.
Curated, human-reviewed deal feed for AI agents — live deal search + price watches. No auth.
Consensus 'best X for Y' rankings from ChatGPT, Claude, Gemini & Grok. Search, verdicts, history.
Smart home product intelligence: 1,080+ products with expert consensus scores and compatibility.
Add one secure layer between your agents and this server.
