Discover games matching your chosen criteria — tags, max price, sale status, platform — optionally personalized to a user's Steam library to exclude owned games.
Discover games by criteria — tags, max price, on-sale, platform — optionally personalized to a user's taste; for filter-based search, not "games like X" (use steam_recommend for that).
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
Changes observed during successful MCP inspections.
v1.18.0Input schema / $defs / DiscoverInput / properties / country_code / titleRemoved value: -"Country Code"Input schema / $defs / DiscoverInput / properties / exclude_owned / titleRemoved value: -"Exclude Owned"Input schema / $defs / DiscoverInput / properties / limit / titleRemoved value: -"Limit"Input schema / $defs / DiscoverInput / properties / max_price / defaultRemoved value: -nullInput schema / $defs / DiscoverInput / properties / max_price / titleRemoved value: -"Max Price"Input schema / $defs / DiscoverInput / properties / on_sale / titleRemoved value: -"On Sale"Input schema / $defs / DiscoverInput / properties / platform / defaultRemoved value: -nullInput schema / $defs / DiscoverInput / properties / platform / titleRemoved value: -"Platform"Input schema / $defs / DiscoverInput / properties / released_within_days / defaultRemoved value: -nullInput schema / $defs / DiscoverInput / properties / released_within_days / descriptionPrevious value: -"Only include games released in the last N days (forces newest-first). Use for 'what came out recently'. Omit for any release date."New value: +"Only include games released in the last N days, ordered by `sort` within that window. Use for 'what came out recently' or 'well-reviewed games from the last year'. Omit for any release date."Input schema / $defs / DiscoverInput / properties / released_within_days / titleRemoved value: -"Released Within Days"Input schema / $defs / DiscoverInput / properties / response_format / $refRemoved value: -"#/$defs/ResponseFormat"Input schema / $defs / DiscoverInput / properties / response_format / enumAdded value: +[
+ "markdown",
+ "json"
+]Input schema / $defs / DiscoverInput / properties / response_format / typeAdded value: +"string"Input schema / $defs / DiscoverInput / properties / sort / titleRemoved value: -"Sort"Input schema / $defs / DiscoverInput / properties / steamid / defaultRemoved value: -nullInput schema / $defs / DiscoverInput / properties / steamid / titleRemoved value: -"Steamid"Input schema / $defs / DiscoverInput / properties / tags / titleRemoved value: -"Tags"Input schema / $defs / DiscoverInput / properties / term / defaultRemoved value: -nullInput schema / $defs / DiscoverInput / properties / term / titleRemoved value: -"Term"Input schema / $defs / DiscoverInput / titleRemoved value: -"DiscoverInput"Input schema / $defs / ResponseFormatRemoved value: -{
- "description": "Output format for tool responses.",
- "enum": [
- "markdown",
- "json"
- ],
- "title": "ResponseFormat",
- "type": "string"
-}Input schema / titleRemoved value: -"steam_discoverArguments"Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "title": "Result",
- "type": "string"
- }
- },
- "required": [
- "result"
- ],
- "title": "steam_discoverOutput",
- "type": "object"
-}New value: +nullv1.14.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already establishes safety, so the bar is lower. The description adds the behavior 'optionally personalized to a user's taste', which hints at reading a user's Steam data, but it does not disclose details like default exclusion of owned games or that unknown tags are ignored. These are in the schema, but the description itself adds only modest behavioral context beyond the annotation.
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 sentence with zero filler. It front-loads the core action ('Discover games by criteria'), lists criteria compactly, mentions optional personalization, and adds the sibling contrast. 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?
The description is adequate for an agent to understand what the tool does and when to choose it, especially with the sibling distinction. However, there is no output schema, and the description doesn't mention the default markdown/json response format, pagination limits, or the behavior of ownership exclusion when steamid is provided. The schema covers the details, but for a tool with this many options, the description leaves some contextual gaps to be inferred.
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 description uses friendly labels ('tags, max price, on-sale, platform') that map to some parameters, but it omits many others (sort, limit, term, country_code, response_format, released_within_days). The input schema itself provides thorough descriptions for every parameter, so the schema carries the parameter-semantic load; the description's contribution is a light mapping, not full compensation.
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 ('Discover games'), then lists concrete criteria (tags, max price, on-sale, platform) and a personalization option. It closes by naming the sibling tool it is not ('not "games like X" (use steam_recommend for that)'), which makes the purpose unmistakable and distinct from the closest sibling.
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 the tool (filter-based search) and when not to ('not "games like X"'), and names the alternative (steam_recommend). It does not mention other sibling tools like steam_search_apps for keyword search or steam_get_featured_specials for curated lists, so the guidance is good but not exhaustive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.