Video game prices from completed eBay and Vinted sales, by platform, region, edition and condition.
Scored across 4 tools
The four tools target distinct actions: listing platforms, searching games, browsing a platform, and fetching detailed sale prices. There is slight overlap because search_games and browse_platform both surface typical prices that get_game_prices later expands, but the descriptions and URL/key dependencies make the intended flow clear.
All tool names use consistent snake_case verb_noun patterns: list_platforms, search_games, browse_platform, get_game_prices. The convention is predictable and readable throughout.
Four tools is well-scoped for a read-only video game price guide. Each tool supports a distinct step in the lookup workflow, with no obvious filler or missing bulk.
The surface covers the core lifecycle: discover platforms, search or browse games, then retrieve detailed sale prices. Minor gaps exist, such as no dedicated game metadata endpoint or collection tracking, but agents can work around these for price-lookup tasks.
One platform's games with their prices, most popular first or by price: the most valuable games on a console, the cheapest, A to Z. Optionally only PAL, NTSC or Japanese releases.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page of games. | |
| sort | No | most-listed (most popular, the default), name (A to Z), price (highest first), price-asc (lowest first). | |
| limit | No | Games a page, 1 to 60 (20 when left out). | |
| region | No | pal, ntsc-u (North America) or ntsc-j (Japan and Asia); every region when left out. | |
| currency | No | Currency for prices, an ISO 4217 code: USD (the default), EUR, GBP, CAD, AUD, JPY, PLN and others. | |
| platform | Yes | A platform slug from list_platforms, e.g. "super-nintendo". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds useful context the annotations do not: results include prices, default ordering is most popular, and region filtering is optional (all regions when omitted). Minor gaps remain around empty results and invalid platform handling.
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 dense sentence with no filler, front-loading the resource and the price payload. The clipped phrasing ('One platform's games') reads slightly fragmented but every clause carries information about content, ordering, or region.
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?
There is no output schema, so the description must say what comes back — it does, stating games plus prices and their ordering. Pagination, page size, region, currency, and the platform slug are fully specified in the schema, and annotations cover the safety profile, leaving no material gap for a 6-parameter 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 100%, with both enums fully documented, so the baseline is 3. The description paraphrases the sort modes ('most valuable', 'cheapest', 'A to Z') but adds no syntax, defaults, or constraints beyond the schema, so it neither compensates nor detracts.
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 resource and scope: one platform's games, including their prices, with ordering options. It is clear what the tool returns, but it never names the sibling tools (search_games, get_game_prices) it must be distinguished from, leaving the agent to infer the boundary.
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: 'One platform's games' suggests browsing a whole catalog rather than search, and the region sentence hints when to narrow results. There is no explicit statement of when to prefer search_games or get_game_prices, nor any prerequisite or exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
What one game sells for, from completed sales: the range and typical price of loose, incomplete, complete, sealed and graded copies, each region's and each edition's price, how fast it sells and its newest sales. Name the game by its page URL from search_games, optionally a region and an edition.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The game's page URL or path, e.g. "https://gamecollecting.app/games/playstation-2/gran-turismo-4". An edition's URL from this tool's answer works too. | |
| sales | No | How many of the newest sales to include, 0 to 10 (10 when left out). | |
| region | No | A region code from the answer's regions, e.g. "us" (NTSC), "eu" (PAL), "asia" (Japan and Asia). | |
| edition | No | An edition slug from the answer's editions, e.g. "platinum". Needs region. | |
| currency | No | Currency for prices, an ISO 4217 code: USD (the default), EUR, GBP, CAD, AUD, JPY, PLN and others. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered externally. The description adds genuine context beyond that — prices derive from completed sales, and the region/edition arguments are values echoed back from a prior answer, implying a chained call pattern. It says nothing about empty results, games without sales history, or caching/staleness of prices, which matters for a read-only analytical tool.
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?
Front-loaded with the outcome ('What one game sells for, from completed sales') followed by the facets, then the invocation instruction. Dense and largely waste-free, though the middle enumeration ('each region's and each edition's price') is slightly awkward to parse.
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?
There is no output schema, so the description carries the burden of describing return values — and it does, covering condition-tier ranges, typical prices, per-region and per-edition prices, sell-through speed and newest sales. Combined with the fully documented 5-parameter schema, an agent has enough to call this 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 every parameter including defaults, bounds and the region/edition dependency is already documented in the schema. The description only restates that region and edition are optional and that the URL comes from search_games. Baseline 3 is appropriate since the schema does the heavy lifting.
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 and resource: what one game sells for from completed sales, then enumerates the exact breakdowns returned (condition tiers, region, edition, sales velocity, newest sales). This is clearly distinguishable from the sibling browse/list/search tools, and it explicitly names search_games as the source of the input.
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?
Establishes the prerequisite workflow — the game must be named by its page URL obtained from search_games — and says region and edition are optional refinements. It does not state when this tool should NOT be used or what to do if a game has no sales data, so it stops short of full conditional guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every platform the price guide covers, with its slug (for the other tools), its number of games and its page URL.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and closed-world scope, so the safety profile is covered; the description adds genuine value by disclosing what each record contains (slug, game count, page URL), which is not derivable from the empty 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?
A single dense sentence with no filler, front-loading the resource and then the returned fields; 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?
With no output schema and no parameters, the description carries the return contract itself and does so fully — an agent knows the shape of each item and what the slug is used for.
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 takes zero parameters, so the baseline of 4 applies; there is nothing for the description to disambiguate on the input side.
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 verb and resource ('Every platform the price guide covers') and enumerates the payload (slug, game count, page URL), which makes it unmistakable against sibling tools like browse_platform or search_games.
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 parenthetical 'its slug (for the other tools)' signals this is the discovery entry point whose slugs feed browse_platform/get_game_prices, giving clear usage context, though it stops short of explicit when-not guidance or naming the siblings outright.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find video games by name, on every platform or one. Each match comes with its platform, its page URL and what loose, complete and sealed copies typically sell for.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page of results, 24 a page. | |
| query | Yes | The game's name or words from it, e.g. "ocarina of time". | |
| currency | No | Currency for prices, an ISO 4217 code: USD (the default), EUR, GBP, CAD, AUD, JPY, PLN and others. | |
| platform | No | A platform slug from list_platforms, e.g. "playstation-2" or "nintendo-switch". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description goes beyond them by disclosing the result shape — platform, page URL, and loose/complete/sealed prices — which is valuable 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?
Two short sentences, zero waste, with the search scope front-loaded before the result payload. Nothing redundant.
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 usefully explains what each match returns, and annotations cover the safety profile. Only minor gaps remain, such as not mentioning pagination behavior, which the schema already documents via the page parameter.
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 query, platform, currency and page parameters are already documented with examples. The description only restates that the search is by name and may span all platforms or one, adding little 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 and resource ('Find video games by name') with the scope of the search ('on every platform or one'). It is clearly distinguishable from browse_platform and list_platforms, though it doesn't explicitly name get_game_prices as the price-detail alternative.
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 'on every platform or one' implies when to pass the platform parameter, but there is no explicit when-to-use guidance relative to the siblings get_game_prices or browse_platform. Usage is inferable rather than stated.
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.
browse_platform2 fields changedInput schema / properties / limitAdded value: +{
+ "description": "Games a page, 1 to 60 (20 when left out).",
+ "maximum": 60,
+ "minimum": 1,
+ "type": "integer"
+}Input schema / properties / page / descriptionPrevious value: -"Page of games, 60 a page."New value: +"Page of games."get_game_prices1 field changedInput schema / properties / salesAdded value: +{
+ "description": "How many of the newest sales to include, 0 to 10 (10 when left out).",
+ "maximum": 10,
+ "minimum": 0,
+ "type": "integer"
+}browse_platformget_game_priceslist_platformssearch_gamesLive catalog of tested retro Nintendo games and Pokémon TCG, with all-in delivered EU prices.
Used prices for GPUs, CPUs, RAM, consoles, iPhones, MacBooks and more from live eBay listings.
Game prices across verified stores, with price history and a buy-now-or-wait verdict.
Swiss market prices for video games and consoles, with provenance. Read-only, OAuth 2.1.
Add one secure layer between your agents and this server.
