Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

mlb_statcast_fielding_run_value

Retrieve Baseball Savant Fielding Run Value leaderboard rows for fielders, teams, batters, or pitchers, with optional dates, splits, sorting, and pagination.

Instructions

Get Baseball Savant Fielding Run Value rows. Returns fielding run value for fielder, fielding-team, batter, batting-team, or pitcher views. Dates and grouping dimensions follow the first-party leaderboard. Minimum 0.1 is available only for fielder and fielding-team views; the batting/pitching views omit it. Sorting and pagination are applied locally. CSV and player-page visualizations are outside this table contract.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoLocal sort field
typeNoTable type
limitNoRows per page (1-500)
offsetNoZero-based row offset (0-5000)
minimumNoTotal minimum; 0.1 only for fielder and fielding-team
team_idNoRepeated MLB team ids
date_endNoEnd date, YYYY-MM-DD, from 2018-03-29 through today
group_byNoRepeated split dimensions
positionNoPosition / position group
sort_dirNoLocal sort direction
game_typeNoGame type
date_startNoStart date, YYYY-MM-DD, from 2018-03-29 through today
season_endNoLast season; must be >= season_start
season_startNoFirst season
minimum_splitNoMinimum within each split; 0.1 only for fielder and fielding-team

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.9

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does disclose real traits: sorting and pagination are applied locally, dates/grouping follow the first-party leaderboard, and minimum 0.1 is restricted to fielder/fielding-team views. It does not cover return shape or any auth/rate context, but the local-processing and scope-boundary notes are genuinely useful beyond the schema.

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?

The purpose is front-loaded in the first sentence, and each subsequent sentence adds a distinct constraint (views, minimum availability, local sort/pagination, exclusions). It is slightly dense but almost every sentence 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?

For a 15-parameter tool with no annotations and no output schema, the description adequately covers scope, view options, the minimum-value quirk, and local processing. With schema coverage at 100%, remaining gaps (exact return fields) are minor, though a brief note on defaults or row contents would round it out.

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% with 9 enums, so the schema already documents all 15 parameters. The description reinforces the minimum-0.1 constraint (already in the schema) but adds little parameter-level syntax or default information, so it stays at the baseline.

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 Fielding Run Value rows,' and enumerates the five view types (fielder, fielding-team, batter, batting-team, pitcher). The resource is distinctive enough to separate it from other mlb_statcast_* siblings, but it never explicitly names a sibling it is or is not, so it stops short of the top score.

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?

It tells the agent which view types exist and that CSV and player-page visualizations fall outside this table contract, which is a partial scope boundary. However, there is no explicit when-to-use guidance or named alternative among the many sibling Statcast tools, leaving selection largely 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