The platform and genre maps. 33 platforms — storefronts, consoles, livestreaming and UGC — with who owns each and where its data lives. 30 genres with definitions, subgenres, example games, and the terms actually used in Chinese, Korean and Japanese. Read the genre map before comparing two datasets: the industry has no shared taxonomy and this records where the vendors disagree.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | Which map. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description must carry behavioral disclosure. It describes content and data provenance but never states read-only behavior, authentication needs, rate limits, or return format; the read-only nature is only implied by "get" and the map content.
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 a one-line subject, then two detail sentences and a usage note. Every sentence carries distinct information; 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?
For a one-parameter read tool with no output schema, the description covers what the data is, why it matters, and when to use it. It omits only operational details like the exact response structure, which are not essential for selecting or invoking the 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 coverage is 100% with a "kind" enum of platforms/genres, so the baseline is 3. The description adds substantial value by explaining what each map contains (storefronts, consoles, livestreaming, UGC; genre definitions, subgenres, example games, CJK terms), which gives the enum values real meaning.
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 identifies the resource as "The platform and genre maps" and enumerates their contents (33 platforms, 30 genres), making the tool's subject unmistakable. It lacks an explicit verb in the prose, relying on the tool name "get" and the noun-phrase description, so it falls just short of a 5.
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?
It gives a concrete trigger: "Read the genre map before comparing two datasets" and explains why (no shared taxonomy, vendors disagree). It does not explicitly rule out siblings like get_market or get_source, so exclusion guidance is absent.
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 distinct resource or action: landscape maps, market profiles, source retrieval, trend listings, source search, and technique search. There is no overlap in purpose, and the descriptions clearly differentiate their roles.
All tool names follow a consistent verb_noun pattern using snake_case (get_, list_, search_). This predictable structure makes the API easy to navigate and reduces cognitive load.
With 6 tools, the surface is well-scoped for a starter pack. Each tool covers a distinct aspect of games research, and the count is within the ideal 3-15 range, neither too thin nor overwhelming.
The tool set covers the core research workflow: understanding landscape, retrieving market profiles, citing sources, exploring trends, and finding sources/techniques. The only minor gap is the absence of a dedicated list of all available markets (get_market requires a code), though search_sources partly fills this, making it workable.
