Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

mlb_statcast_running_game_details

Retrieve Baseball Savant running game play details by entity_id, expanding a pitcher or pitching-team row into individual attempted-running plays.

Instructions

Get Baseball Savant Running Game play details. Returns individual attempted-running plays expanded from a pitcher or pitching-team Running Game row. Pass its entity_id and repeat the same table filters. For team-stint rows, pass that row's team id; League rows do not expose a detail feed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nNoMinimum pitcher opportunities
teamNoOne MLB team id; use the row's team id for split-team rows
typeNoDetail group
limitNoPlay rows per page, 1-500
splitNoReturn separate year rows
offsetNoZero-based play-row offset
prior_pkNoPrior pickoff/disengagement count
entity_idYesPositive player or team entity id from the Running Game leaderboard
game_typeNoGame scope
pitch_handNoPitcher's throwing hand
season_endNoInclusive last season
target_baseNoTarget base
runner_movedNoRunner movement outcome
season_startNoInclusive first season
with_team_onlyNoRestrict player rows to selected team; only valid with a specific team and Pit type

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.9

TDQS

A4.2/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the useful constraint that League rows have no detail feed, but says nothing about the read-only nature, pagination behavior (limit/offset exist), or the return shape for a 15-parameter tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with the core action front-loaded and the entity_id/team guidance following. No filler; every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the parent-row relationship, entity_id derivation, filter repetition, and the League-row exclusion, which is strong for a 15-param tool with no annotations. The main gap is the absence of any return-format or pagination note given there is no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 15 parameters including the 11 enums. The description adds context on entity_id provenance and the team-stint case, but does not enrich the semantics of the remaining filters beyond the schema's own descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Get) and resource (Baseball Savant Running Game play details) and precisely scopes it: individual attempted-running plays expanded from a pitcher or pitching-team Running Game row. This clearly distinguishes it from the sibling mlb_statcast_running_game leaderboard tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit invocation guidance: pass the entity_id from the Running Game row and repeat the same table filters, use the row's team id for team-stint rows. It also names a when-not condition (League rows do not expose a detail feed), leaving little to inference.

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

Deploy Server

Other Tools