Aggrometer's signature metric: aggro = live Twitch viewers / concurrent Steam players, same hour, per game (min 500 players). Above 1.0 means more people watch than play — spectacle games, watch-to-learn genres. A sudden aggro jump is an early attention signal.
| Name | Required | Description | Default |
|---|---|---|---|
| genre | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Because no annotations are provided, the description carries the full burden of behavioral disclosure. It does add useful context: the formula, same-hour per-game aggregation, the min 500 player threshold, and the >1.0 interpretation. But it omits output shape, ordering, pagination, and how the optional genre parameter changes behavior.
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 three sentences with no filler: first defines the metric, second explains what values mean, third gives a signal use case. It is front-loaded and efficient, though some interpretive prose could have been replaced with operational detail.
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 annotations, the description needs to explain what the tool returns and how the genre parameter works. It explains the aggro concept well but leaves out essential invocation and response details, making it incomplete for an agent deciding how to call it.
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% and the description never mentions the only parameter, 'genre'. The agent cannot infer whether genre filters results, groups them, or changes the metric calculation. This is a significant gap because the description must compensate for the undocumented schema but does not.
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 defines the aggro metric (live Twitch viewers / concurrent Steam players) and its interpretation, but it never states the tool's actual operation—no verb like 'list', 'compute', or 'return'. It tells the agent what aggro means, not explicitly what aggro_board does or returns.
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 a use case ('A sudden aggro jump is an early attention signal') and notes watch-to-learn genres, which hints at when the tool might be relevant. However, it does not compare against siblings like hype_board, top_watched, or top_played, nor does it state when not to use this tool.
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.
Each tool targets a clearly distinct slice of the domain: per-game detail, genre aggregates, top lists, released-game aggro, unreleased-game hype, search, and warehouse status. Even the two 'board' tools are unambiguous because one is explicitly for live/released games and the other for unreleased anticipation.
Tool names are all lowercase snake_case and generally readable, but they mix conventions: noun-style names like game_detail and genre_rollup sit alongside verb-style names like get_summary and search_games, plus adjective-style names like top_played and top_watched. The pattern is not chaotic, but it is inconsistent enough to be a minor usability issue.
Eight tools is a well-scoped size for an analytics server covering catalog lookup, detailed game profiles, genre rollups, top lists, and specialized signal boards. Each tool earns its place and there is no obvious redundancy.
The surface covers the core workflows: understand data coverage, search for games, inspect a game, view rankings, see genre-level aggregates, and check both released-game and unreleased-game attention signals. A minor gap is the lack of a direct per-game aggro score endpoint, though the underlying data in game_detail makes this derivable.