recently_playedList games played by a SteamID64 in the last two weeks, with playtime in the last 2 weeks and total playtime. Optional count caps results.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | ||
| steamid | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| response | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the description does not need to restate safety. It adds behavioral context beyond annotations by specifying the time range (last two weeks) and the return fields (playtime in last 2 weeks and total playtime), which helps the agent understand what to expect.
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 that is front-loaded with the action and resource, followed by output details and the optional parameter. Every word earns its place; there is no redundancy or 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?
Given the tool's simplicity, the annotations, and the presence of an output schema, the description covers the essential purpose, parameter semantics, and scope. Minor ambiguities (e.g., exact sorting or zero-playtime handling) are not critical for a read-only, idempotent 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?
The input schema has 0% description coverage, so the description must compensate. It does: 'SteamID64' clarifies the steamid format, and 'Optional count caps results' explains the count parameter's effect. This adds meaningful semantics beyond the bare 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?
The description clearly states the action ('List games played'), the target resource ('by a SteamID64'), and the time scope ('in the last two weeks'). It also mentions the included playtime data, making it distinct from owned_games and other Steam tools. This is a specific verb+resource+scope formulation.
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's use case (recently played games in a two-week window) but does not explicitly state when to use it over alternatives like owned_games or player_stats. It provides clear context but no exclusions or comparisons to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools overlap significantly: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical variants, while deep_research, discover_tools, and suggest_questions all serve meta/onboarding purposes. The Steam-specific tools are distinct, but they are drowned out by a large unrelated set (Polymarket, Pipeworx, npm scanning) that makes selection confusing.
Tool names follow no single convention: some are verb_noun (resolve_vanity_url, generate_llms_txt), some are noun-only (app_details, player_stats), and others use domain prefixes inconsistently (polymarket_arbitrage, ask_pipeworx_grounded, deep_research). The mix of descriptive and vague names (process, run, execute) adds to the inconsistency.
At 45 tools, the server is heavily overloaded, especially for a server named 'Steam' where only about a third of the tools actually relate to Steam. The rest belong to Pipeworx, Polymarket, and other unrelated domains, making the scope unclear and the tool count far too large for a focused purpose.
For the Steam domain, the server covers a reasonable range: app details/news, player counts, friends, owned games, achievements, stats, bans, levels, and summaries. However, notable gaps exist such as store search, reviews, wishlist, or any user inventory/trading features. The non-Steam tools add breadth but do not address these missing Steam operations.