nba_stats_call

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds valuable behavioral detail beyond the annotations: it discloses the column-oriented response format ({resultSets:[{name, headers, rowSet}]}) and instructs to zip headers with rows. It also notes that no auth is needed and that guessing an operation returns an error (in the schema description). This enriches the agent's understanding of how the tool behaves.

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 compact yet information-dense. It front-loads the purpose, then covers usage guidance, resource reference, response format, and authentication in a logical flow. Every sentence 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?

For a tool that wraps 138 possible operations, the description is remarkably complete. It covers invocation, default param behavior, where to browse operations, the common response shape, and auth requirements. It appropriately points to the catalogue resource for operation-specific details, so the agent knows where to look for the rest. The presence of rich annotations and full schema descriptions further complements this.

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?

With 100% schema description coverage, the baseline is 3, but the description meaningfully adds to the schema: it explains that operation is a '/stats/ path segment' and that query_params overrides the pre-loaded default parameter set, giving a concrete example ({Season: '2024-25', PlayerID: '201939'}). This goes beyond the schema's generic descriptions and helps the agent construct correct calls.

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 opens with 'Gateway to the stats.nba.com /stats/ analytics API (138 operations)', giving a clear verb ('Gateway') and specific resource. It lists concrete operation examples (e.g., 'leaguedashplayerstats', 'shotchartdetail') that are distinct from the sibling NBA-specific tools, making its role as a raw API gateway unambiguous. Though it doesn't explicitly say 'use this instead of balldontlie_nba_stats', the specificity of the resource and operations differentiates it well.

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 tells the user exactly what to supply (operation and query_params), explains that each operation has NBA's full default param set and only overrides are needed, and directs to the nba://stats/operations resource for full details. It doesn't explicitly name alternative tools or exclusion criteria, but the usage context is clear and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.