Retrieve a user's Steam friends with their display names and current online status. Supports pagination, filtering by online-only, and output in markdown or JSON.
List a user's Steam friends, enriched with name and current status.
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
Changes observed during successful MCP inspections.
v1.18.0Input schema / $defs / FriendListInput / properties / limit / titleRemoved value: -"Limit"Input schema / $defs / FriendListInput / properties / offset / titleRemoved value: -"Offset"Input schema / $defs / FriendListInput / properties / online_only / titleRemoved value: -"Online Only"Input schema / $defs / FriendListInput / properties / response_format / $refRemoved value: -"#/$defs/ResponseFormat"Input schema / $defs / FriendListInput / properties / response_format / enumAdded value: +[
+ "markdown",
+ "json"
+]Input schema / $defs / FriendListInput / properties / response_format / typeAdded value: +"string"Input schema / $defs / FriendListInput / properties / steamid / defaultRemoved value: -nullInput schema / $defs / FriendListInput / properties / steamid / titleRemoved value: -"Steamid"Input schema / $defs / FriendListInput / titleRemoved value: -"FriendListInput"Input schema / $defs / ResponseFormatRemoved value: -{
- "description": "Output format for tool responses.",
- "enum": [
- "markdown",
- "json"
- ],
- "title": "ResponseFormat",
- "type": "string"
-}Input schema / titleRemoved value: -"steam_get_friend_listArguments"Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "title": "Result",
- "type": "string"
- }
- },
- "required": [
- "result"
- ],
- "title": "steam_get_friend_listOutput",
- "type": "object"
-}New value: +nullv1.14.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true already establishes this as a safe read-only operation, and 'List' is consistent with that. The description adds the useful enrichment detail ('name and current status'), but it does not disclose pagination behavior, privacy limitations, or error/rate-limit behavior. With annotations covering safety, this is adequate but not rich.
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 no filler: main action first, resource second, and enrichment last. It is immediately scannable and every word contributes meaning.
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 annotations and schema cover safety and arguments, but there is no output schema and the description only says the result is 'enriched with name and current status.' It does not mention the markdown/json response_format option, pagination, or cases where friend data may be unavailable or private. This is adequate for a simple read-only list tool but has clear gaps.
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 nested schema fully documents all effective parameters (limit, offset, steamid, online_only, response_format), including the steamid fallback behavior. The tool description itself adds no parameter-level meaning, but because the schema does the heavy lifting, the baseline of 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?
Description opens with a specific verb ('List') and a clear resource ('a user's Steam friends'), then adds 'enriched with name and current status' to define the output. This distinguishes it from siblings like steam_get_player_summary, which targets a single player summary rather than the friend list.
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 gives no guidance on when to use this tool versus alternatives, nor does it mention when to omit steamid to fall back to the configured STEAM_USER. With many sibling tools that involve players and friends, the selection context is left entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.