Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

mlb_statcast_bat_tracking

Query Baseball Savant bat-tracking rows for batters, pitchers, teams, or leagues; filter by season, date, count, pitch type, contact, and attack zone.

Instructions

Get Baseball Savant bat-tracking rows. Returns batter, batting-team, pitcher, pitching-team, or league bat-tracking rows with the live page's season, game type, swing threshold, date, side, contact, attack zone, team, pitch, count, and grouping filters. Use mlb_discovery for the same complete value sets. Multi-value filters are passed as repeated query parameters.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoLocal row sort field
typeNoTable row type
limitNoRows per page (1-500)
teamsNoOne or more MLB team ids
countsNoOne or more ball-strike counts
offsetNoZero-based row offset
bat_sideNoBatter side
date_endNoOptional date range end in YYYY-MM-DD
group_byNoUp to four grouping columns
sort_dirNoSort direction
game_typeNoGame type
date_startNoOptional date range start in YYYY-MM-DD
min_swingsNoMinimum swing qualifier
pitch_handNoPitcher hand
season_endNoLast season; must be >= season_start
attack_zoneNoAttack zone
is_hard_hitNoHard-hit filter
pitch_typesNoOne or more pitch types
contact_typeNoContact type
season_startNoFirst season
min_group_swingsNoMinimum swings per grouped row

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.9

TDQS

A3.6/5.0
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 burden. It discloses the calling convention for multi-value filters ('passed as repeated query parameters'), which is useful, but says nothing about auth requirements, rate limits, or pagination behavior despite limit/offset parameters existing. Partial disclosure for a 21-param read tool.

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?

Three sentences, front-loaded with the purpose and row types, then filters, then the discovery pointer and calling convention. The middle filter list is long but each term maps to an actual parameter, so it largely earns its place.

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?

With no output schema and no annotations, the description must stand alone, and it covers what rows are returned, what filters apply, and the multi-value convention. It could say more about pagination and result shape, but for a query endpoint with fully documented params it is largely sufficient.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real value beyond the schema by specifying that multi-value filters (teams, counts, group_by, pitch_types) are serialized as repeated query parameters — a detail not present in the schema. It also groups the filters by category.

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

Purpose4/5

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

States a specific verb and resource ('Get Baseball Savant bat-tracking rows') and enumerates the row types it returns (batter, batting-team, pitcher, pitching-team, league). It is clearly distinct from sibling statcast endpoints like swing_path or swing_timing, though it does not explicitly contrast with them.

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

Usage Guidelines3/5

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

The only routing guidance is 'Use mlb_discovery for the same complete value sets', which tells the agent where to look up enum values rather than when to prefer this tool over alternatives. There is no explicit when-to-use or when-not-to-use statement.

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