Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

mlb_statcast_baserunning

Fetch Baseball Savant baserunning leaderboard tables and filter, sort, or page underlying JSON rows for run value, basestealing, and extra bases taken analysis.

Instructions

Get Baseball Savant baserunning leaderboard tables. Returns Baseball Savant Baserunning Run Value, Basestealing, or Extra Bases Taken tables. All filter value sets were read from the live first-party controls; rows are embedded in the page response and searched, sorted, and paged locally. Use mlb_discovery.statcast_baserunning_filters for board-specific groups, thresholds, and sort fields. CSV and visual expansion modes are excluded; this returns the underlying JSON table rows.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nNoBoard-specific row threshold
sortNoLocal sort field; accepted values depend on board
teamNoMLB team id or split-team rows
typeNoBoard group; accepted values depend on board
boardYesBaseball Savant table
limitNoRows per page, 1-500
splitNoReturn separate year rows
offsetNoZero-based row offset
searchNoCase-insensitive substring in the displayed player or team name
prior_pkNoBasestealing prior pickoffs
sort_dirNoLocal sort direction
game_typeNoGame scope
pitch_handNoBasestealing pitcher hand
season_endNoInclusive last season
target_baseNoBasestealing target base
key_base_outNoExtra Bases Taken situation
runner_movedNoBasestealing runner outcome
season_startNoInclusive first season
with_team_onlyNoRestrict to selected team's active player rows; requires a specific team id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.9

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does well: it discloses that filter sets were read from live first-party controls, that rows are embedded in the page response, and that search/sort/paging happen locally rather than server-side. This local-pagination behavior is important context for interpreting offset/limit/sort, though it omits auth or rate-limit notes.

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

Conciseness4/5

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

Four sentences, front-loaded with purpose and return scope, followed by the routing pointer and the local-processing caveat. Dense but every sentence carries information; no filler.

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?

For a 19-parameter tool with no annotations and no output schema, the description covers what is returned (JSON table rows), where valid filter values live, and the local search/sort/page behavior. It does not describe the row shape, but given full schema coverage and no output schema, the remaining gap is minor.

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 19 parameters; baseline is 3. The description adds the useful fact that accepted group/threshold/sort values are board-dependent and points to a discovery tool, but offers no syntax or format detail beyond what the schema provides.

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') plus resource ('Baseball Savant baserunning leaderboard tables') and enumerates the three concrete boards it can return (Run Value, Basestealing, Extra Bases Taken). This distinguishes it cleanly from sibling tools like mlb_statcast_running_game or mlb_statcast_running_game_details.

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

Usage Guidelines4/5

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

Explicitly routes the agent to mlb_discovery.statcast_baserunning_filters for board-specific groups, thresholds, and sort fields, and notes that CSV/visual expansion modes are excluded. It stops short of explicitly contrasting when to use this versus the sibling running_game detail tools, but the filter-discovery pointer gives clear actionable context.

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