Full contract for one table: fields with types and descriptions, the filters query_table accepts (with operators like __gte/__lte/__between/__like and required filter combinations), page-size limits, primary key, and a runnable example URL. No credentials needed. Always call this before query_table — filters not listed here are rejected.
| Name | Required | Description | Default |
|---|---|---|---|
| table | Yes | ||
| league | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and excels: it details what the response contains (fields, filters, page-size limits, primary key, example URL), states that unlisted filters are rejected, and clarifies authentication requirements. This is richer than a simple read-only hint.
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?
Two sentences with front-loaded core info; the first sentence enumerates the contract elements, and the second provides actionable constraints. No filler or redundancy.
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?
Despite lacking an output schema, the description enumerates return contents (fields, filters, limits, primary key, example URL) and adds usage constraints, making the tool fully understandable for a 2-parameter metadata lookup.
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 schema has 0% description coverage, so the description must compensate. It clarifies the tool's purpose but does not explicitly define the 'table' parameter beyond 'one table' or specify how league relates to table selection. The league enum is self-documenting, but table string semantics are left to inference.
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 states the tool provides the 'Full contract for one table' with fields, filters, limits, primary key, and example URL. This clearly identifies it as a schema/metadata introspection tool, distinct from siblings like query_table and list_tables.
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 explicit instruction: 'Always call this before query_table' and warns that filters not listed are rejected. Also notes 'No credentials needed,' providing clear when-to-use context and setting expectations.
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 purpose: metadata discovery (list_leagues, list_tables, describe_table), data retrieval (query_table, get_record, graphql_query), convenience queries (games_on_date, game_markets, search_players), and account management (api_usage). No two tools have overlapping boundaries despite some sharing the ability to access data.
Most tools follow a clear verb_noun pattern (describe_table, get_record, list_leagues, list_tables, query_table, search_players), but a few use noun-only names (api_usage, game_markets, games_on_date, graphql_query). The naming is still readable and lowercase snake_case throughout, but the mix prevents a perfect score.
10 tools is well-scoped for a sports data API: it provides the essential discovery, schema inspection, querying, and retrieval operations, plus a few convenience wrappers. The count is neither too thin nor bloated.
The tool set fully covers the lifecycle of a read-only data API: exploring available leagues/tables, understanding table schemas, querying with filters and pagination, fetching by primary key, and accessing relational data via GraphQL. Convenience tools for games, markets, and player search address common use cases, and any data not directly exposed can be accessed through query_table.
