Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

mlb_statcast_arm_angle

Fetch MLB pitcher arm angle rows from Baseball Savant with league-average reference, filtered by season, team, pitch type, hand, date, and group-by. Sort and paginate locally.

Instructions

Get Baseball Savant Pitcher Arm Angle rows. Returns Pitcher Arm Angle table rows and the matching MLB-average reference. Supports season, team, game type, pitch type, hand, batter side, pitch-count thresholds, date range, and up to four group-by selectors. Table sorting and pagination run locally. Visualization-only controls, animation, and CSV output are separate formats.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
minNoMinimum total pitches; defaults to q.
sortNoLocal table sort field; defaults to arm_angle.
limitNoRows per page (1-500).
teamsNoMLB team ids; omit for all teams.
offsetNoZero-based row offset (0-5000).
seasonsNoSeasons; at most three may be combined. Defaults to 2026.
bat_sideNoBatter side; omit for both.
date_endNoInclusive end date, YYYY-MM-DD.
group_byNoUp to four grouping fields.
sort_dirNoLocal sort direction; defaults to asc.
date_startNoInclusive start date, YYYY-MM-DD.
game_typesNoGame type codes; defaults to R.
pitch_handNoPitcher throwing hand; omit for both.
pitch_typesNoPitch type codes; defaults to FF.
min_group_pitchesNoMinimum pitches per group; defaults to 1.

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 full burden and does disclose meaningful traits: the MLB-average reference is bundled with the rows, and sorting/pagination run locally rather than server-side. It omits any note on auth, rate limits, or dataset size, but for a read-only Statcast table this is reasonably transparent.

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?

Purpose and return contents are front-loaded and the sentences are dense, but the first two sentences overlap ('Get ... Arm Angle rows' / 'Returns ... Arm Angle table rows'), a minor redundancy.

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 15-parameter, no-output-schema, no-annotation tool, the description covers the return payload, the local sort/pagination semantics, and the group-by cap, which are the non-obvious items. Missing only dataset-size/performance expectations given that sorting and paging are local.

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 each of the 15 parameters is already documented with enums and defaults. The description's enumeration of parameter categories adds no syntax or format detail beyond what the schema supplies, so the baseline 3 applies.

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?

Names the specific source (Baseball Savant), the resource (Pitcher Arm Angle table rows), and what is returned (rows plus the matching MLB-average reference). This distinguishes it from the many adjacent mlb_statcast_* siblings such as arm_strength and arm_value.

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?

Lists the supported selectors (season, team, game type, pitch type, hand, batter side, thresholds, date range, group-by) and explicitly excludes visualization-only controls, animation, and CSV output as separate formats. It does not, however, route between this table and neighboring arm-related Statcast tools, so an agent must infer the choice.

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