mlb_statcast_running_game

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

No annotations are provided, so the description carries the burden and it does well: it discloses exactly which controls are server-side live-verified versus applied locally (sorting, player/team search, pagination), which is critical for an agent to know that local sort/search semantics differ from MLB.com's. It does not describe pagination defaults or the return shape, but given zero structured behavioral hints this is strong context.

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-loads the purpose and result shape in the first sentence, then uses subsequent sentences for routing and behavioral clarifications. It is dense but every clause (sibling routing, live-verified vs local, expanded-column, CSV) conveys distinct information; the enumeration of control groups is mild filler since the schema covers them.

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 17 parameters, no annotations, and no output schema, the description does the necessary work: it clarifies the result entity scope, routes to the per-play sibling, and explains which filters are verified server-side versus applied locally. It omits default sort/pagination behavior, which would help an agent predict the unfiltered result set, keeping it from a 5.

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 100% and 13 of 17 parameters have enums, so the schema already documents every parameter's meaning and allowed values. The description adds minimal per-parameter detail beyond a prose enumeration of the control categories (season/game, hand, runner movement, target base, prior pickoff count, minimum opportunities, team, team-stint). Baseline 3 is appropriate because the schema does the heavy lifting.

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?

States a specific verb ('Get'), a named resource ('Baseball Savant Running Game leaderboards'), and the exact entity groupings it returns (pitchers, pitching teams, league). It distinguishes itself from the per-play sibling by naming mlb-statcast-running-game-details as the place for play-level data.

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?

Explicitly routes the agent: says use this for the leaderboard table and directs per-play lookups to mlb-statcast-running-game-details. Also clarifies two behavioral edge cases (expanded-column toggle, CSV download) so the agent does not misroute those requests.

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