Cross-source price compare for clothing musicians designed, wore, or founded. Real listings.
Scored across 4 tools
The four tools occupy distinct layers: get_facets returns filter vocabulary, list_collections returns the artist/brand taxonomy, search_pieces finds garments, and get_piece drills into one garment's listings. Descriptions even encode the call order (search_pieces then get_piece). The only mild overlap is between list_collections and a collection-filtered search_pieces, since both serve discovery.
All four names follow the same verb_noun snake_case pattern: get_facets, get_piece, list_collections, search_pieces. Verbs are used precisely — list for enumerations, search for queries, get for single-resource retrieval.
Four tools cover the read-only browse→search→detail flow cleanly, with no redundant entries. It is slightly lean for a multi-platform resale catalogue (no explicit pagination or bulk-listing tool), but nothing feels missing at the surface level.
Full lifecycle for a read-only aggregator is present: taxonomy, facets, search, and per-piece listing detail with buy links, so no dead ends in the core workflow. Minor gaps exist — no bulk/multi-piece fetch, no saved-search or price-history capability — but these are workarounds, not blockers.
Return the values that actually exist in the catalogue for filtering a search: sizes, conditions, source platforms, artists, designers, and the price range.
Use this before search_pieces when you want to build a precise query from real values rather than guesses. For example, to check which sizes of a garment are genuinely listed right now, or which platforms currently carry a given collection.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds that it returns 'values that actually exist in the catalogue', reinforcing real-time snapshots. No contradiction; slightly adds context beyond 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?
Two short paragraphs: first states what it returns, second gives usage guidance. Every sentence is purposeful, with no redundancy. Front-loaded with core function.
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?
Given no parameters and no output schema, the description adequately covers what facets are returned and when to use. With annotations providing safety and idempotency context, it's fully informative for agent decision-making.
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?
No parameters exist, so baseline is 4. The description adds value by listing the types of facets returned (sizes, conditions, etc.), which the schema cannot convey. This fully compensates for missing parameter details.
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 it returns facet values for filtering, specifying categories like sizes, conditions, artists. It distinguishes from sibling tools like search_pieces (used for actual searching) and get_piece/list_collections, making the purpose unambiguous.
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?
Explicitly advises using this tool before search_pieces to build precise queries from real values, with examples like checking sizes or platforms. This provides clear guidance on when to use versus alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the complete set of live resale listings for one specific garment, with a direct buy link for each.
Call search_pieces first: it returns the collectionId and pieceId this tool needs.
Use this once someone has settled on a specific piece and wants every option available: all platforms, all sizes, all conditions, with prices wherever a live feed provides one. For example, after a search surfaces the Ivy Park Drip 2 Oversized Hoodie, use this to show every listing of it currently for sale and where to buy each one.
| Name | Required | Description | Default |
|---|---|---|---|
| pieceId | Yes | ||
| collectionId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds context: returns 'live resale listings', 'direct buy link', 'all platforms, all sizes, all conditions, with prices wherever a live feed provides one.' No contradictions.
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 concise, with three paragraphs each providing essential information. No fluff or redundant statements.
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?
No output schema exists, but the description explains the output: 'live resale listings with direct buy link', 'all platforms, all sizes, all conditions, with prices.' It mentions that pieces have a collectionId and pieceId and that this tool is used after search_pieces. Complete for a detailed lookup 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%, but the description explains that pieceId and collectionId come from search_pieces and are needed for identifying the garment. It does not describe each parameter individually, but the added context about where to get the IDs compensates.
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 verb 'Get' and the resource 'the complete set of live resale listings for one specific garment, with a direct buy link for each.' It distinguishes from siblings by mentioning that search_pieces is called first and that this tool provides all listings for a specific piece.
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 explicitly says when to use: 'Use this once someone has settled on a specific piece and wants every option available.' It also provides a prerequisite: 'Call search_pieces first: it returns the collectionId and pieceId this tool needs.' Does not explicitly state when not to use, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the collections besot indexes: collaborations between the people we obsess over and design houses, capsule drops, and brands they founded and own.
Use this when someone asks what a given artist has made, which artists have worked with a given brand, or what is covered before running a search. For example: what fashion has Harry Styles designed; which artists have collaborated with adidas; what Beatles clothing collections exist.
Coverage includes Harry Styles (Gucci HA HA HA, Pleasing), Beyonce (Ivy Park with adidas), Oasis, Liam Gallagher and Noel Gallagher (adidas), and The Beatles (Comme des Garcons, Stella McCartney, Alice + Olivia), and grows as new fandoms are added.
Filter by artist, or by type: collaboration, capsule, or artist-founded brand.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Collab, Capsule, or Own brand | |
| artist | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnlyHint, idempotentHint, openWorldHint, and destructiveHint, so the description need not repeat those. It adds useful context that coverage 'grows as new fandoms are added' and notes filtering behavior, but it does not disclose return format or pagination, which are absent from annotations and 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?
The description is a bit long but organized: purpose, when-to-use, coverage examples, and filters. The first sentence is slightly awkward ('besot indexes') and the coverage examples add length, but each section earns its place by helping an agent decide when to call the tool.
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 read-only browse tool with two optional filters and no output schema, the description provides purpose, usage timing, coverage, and parameter behavior in natural language. It does not describe the shape of returned collection objects, but that is a minor gap given the simple list semantics.
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 only 50% because artist has no description. The description compensates by explaining both filters: 'Filter by artist, or by type: collaboration, capsule, or artist-founded brand,' and the examples make the artist filter concrete with names like Harry Styles and Beyonce. This adds meaning beyond the schema's minimal type description.
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 a specific verb and resource: 'List the collections besot indexes' and immediately defines the resource as collaborations, capsule drops, and artist-founded brands. It differentiates from siblings by framing this as the coverage/browse tool while search_pieces is implied as the search path.
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?
It gives explicit when-to-use guidance: 'Use this when someone asks what a given artist has made, which artists have worked with a given brand, or what is covered before running a search' with concrete examples. It does not explicitly name sibling tools as alternatives or state when not to use it, so it lacks the full when-not/alternatives specificity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find where to buy a specific piece of clothing or footwear connected to the people we obsess over, and get every live resale listing for it in one call.
Use this when someone asks questions like: where can I buy the Gucci HA HA HA blazer; is the Ivy Park Drip 2 hoodie listed in a medium; what is the Pleasing crewneck going for right now; which platforms have the Oasis adidas Original Forever trainers in a UK 9; what Beatles Comme des Garcons pieces are on the resale market today.
Most of these garments are sold out at retail and exist only on resale, scattered across marketplaces under inconsistent seller titles. besot gives each garment one canonical name and pulls the live listings for that exact piece from eBay, StockX, GOAT, The RealReal, Vestiaire, Grailed, Poshmark, Mercari and Depop.
Covers clothing and footwear that the people we obsess over designed, founded, were the inspiration for, or wore. Takes plain language in q (for example "Ivy Park Drip 2 hoodie" or "Harry Styles Gucci blazer"), with optional filters for artist, brand, collection, garment type, size, condition, source platform, and price range.
Every listing returned carries the platform, size, condition, price (approximate USD, null when the seller did not state one), and a direct buy link.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Free text over piece name, collection, artist, brand, and garment vocabulary. Product names are canonical (Gazelle, Firebird Track Top), so plain garment words work too, in British or American English: trainers or sneakers, jumper or sweater, trousers or pants, trackie or tracksuit. | |
| size | No | Match a listing size; call get_facets for valid values | |
| sort | No | ||
| type | No | COLLECTION type: Collab, Capsule, or Own brand. For the garment, use category. | |
| brand | No | Designer/brand name | |
| limit | No | 1-50, default 20 | |
| artist | No | ||
| source | No | Resale platform, e.g. ebay, grailed, therealreal | |
| category | No | GARMENT category, one of: footwear, outerwear, tops, knitwear, hoodies, bottoms, one-pieces, suits, sets, accessories, eyewear, swim-active | |
| maxPrice | No | ||
| minPrice | No | ||
| condition | No | ||
| collection | No | Collection id (exact) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and open-world, so the safety profile is covered; the description adds genuinely new behavior — that listings are aggregated live from nine named platforms, that besot normalizes inconsistent seller titles to one canonical garment name, and that prices are approximate USD and null when unstated. The main omission is pagination/total-count behavior for a tool capped at 50 results.
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 is front-loaded in the first sentence, but the body runs five paragraphs with repetition — the 'people we obsess over' framing and the retail-sold-out rationale are each restated, and the nine-platform list duplicates what the source parameter already enumerates. The example queries earn their space; the surrounding prose could be cut by a third without losing 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?
For a 13-parameter search tool with no output schema, the description does the important work of describing the return shape (platform, size, condition, approximate USD price, direct buy link). It stops short of covering result ordering, total result counts, or what an empty result means for a sold-out piece, which matters given the 'sold out at retail' premise.
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?
At 62% schema coverage the description compensates by enumerating the filter axes (artist, brand, collection, garment type, size, condition, source platform, price range) and by giving plain-language q examples plus the British/American vocabulary hint. It does not resolve the type-vs-category ambiguity that the schema flags, and it calls the garment filter 'garment type' while the actual parameter is 'category' — a small but real mismatch.
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 ('Find where to buy') applied to a specific resource ('a specific piece of clothing or footwear connected to the people we obsess over') and adds the outcome ('every live resale listing for it in one call'). The scope sentence about garments sold out at retail and scattered across marketplaces makes it clearly distinguishable from get_piece (detail lookup) and get_facets (value enumeration).
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?
Provides five concrete example questions that map directly onto use cases ('is the Ivy Park Drip 2 hoodie listed in a medium', 'what is the Pleasing crewneck going for right now'), which is stronger than generic when-to-use prose. However, it never names a sibling or states when NOT to use it — e.g. that get_piece should be used once a piece is already identified, or get_facets for valid size values.
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_pieces3 fields changedInput schema / properties / categoryAdded value: +{
+ "description": "GARMENT category, one of: footwear, outerwear, tops, knitwear, hoodies, bottoms, one-pieces, suits, sets, accessories, eyewear, swim-active",
+ "maxLength": 100,
+ "type": "string"
+}Input schema / properties / q / descriptionPrevious value: -"Free text over piece name, collection, artist, brand"New value: +"Free text over piece name, collection, artist, brand, and garment vocabulary. Product names are canonical (Gazelle, Firebird Track Top), so plain garment words work too, in British or American English: trainers or sneakers, jumper or sweater, trousers or pants, trackie or tracksuit."Input schema / properties / type / descriptionPrevious value: -"Collab, Capsule, or Own brand"New value: +"COLLECTION type: Collab, Capsule, or Own brand. For the garment, use category."get_piece2 fields changedInput schema / properties / collectionId / maxLengthAdded value: +200Input schema / properties / pieceId / maxLengthAdded value: +200list_collections2 fields changedInput schema / properties / artist / maxLengthAdded value: +200Input schema / properties / type / maxLengthAdded value: +100search_pieces9 fields changedInput schema / properties / artist / maxLengthAdded value: +200Input schema / properties / brand / maxLengthAdded value: +200Input schema / properties / collection / maxLengthAdded value: +200Input schema / properties / condition / maxLengthAdded value: +100Input schema / properties / q / maxLengthAdded value: +500Input schema / properties / size / maxLengthAdded value: +100Input schema / properties / sort / maxLengthAdded value: +100Input schema / properties / source / maxLengthAdded value: +200Input schema / properties / type / maxLengthAdded value: +100get_facetsget_piecelist_collectionssearch_piecesSearch fashion across 1,000+ retailers; compare prices, sizes and stock by country.
Search and explore taste-led finds in clothing, audio, designed objects and music.
Live sneaker & streetwear prices and in-stock sizes across 600+ US stores, by style code.
GDPR-clean secondhand listings and sold comps for resale pricing research. No seller personal data.
Add one secure layer between your agents and this server.