Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

mlb_statcast_year_to_year

Retrieve MLB Baseball Savant year-to-year changes for batters, pitchers, or teams by choosing a stat type and comparison start year; returns yearly values and differences.

Instructions

Get Baseball Savant Year-to-Year Changes. Returns one of Baseball Savant's Year-to-Year Changes tables for batters, pitchers, batting teams, or pitching teams. Select one of the live statistic types and comparison start years; the page data contains available yearly values and differences. Table sorting and pagination are applied locally. Use mlb_discovery for all accepted group, type, and year values.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoLocal sortable column; name_display_last_first, year_YYYY, TYPE_YYYY, or TYPE_diff_YYYY. Defaults to the selected metric's difference for the selected comparison year.
typeNoStatistic type
yearNoComparison start year; compares this season with the following year
groupNoTable group
limitNoRows per page (1-500)
offsetNoZero-based row offset (0-5000)
sort_dirNoSort direction; defaults to Batter descending and Pitcher ascending

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.9

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that sorting and pagination are applied locally (client-side), implying the page data arrives whole, and clarifies that comparison years produce yearly values and differences. It does not address read-only status explicitly, auth, or return shape beyond a high-level mention.

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?

Front-loaded with the purpose, followed by scoping, value sourcing, and a local-sorting note. The opening sentence slightly restates the tool name, but overall there is little waste.

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?

No output schema or annotations exist, and the description covers purpose, group scopes, valid-value sourcing, and client-side sorting/pagination. It is adequate for a 7-parameter read tool, though it could say more about how the comparison year maps to output columns.

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 description coverage is already 100%, so the baseline is 3. The description adds real value by pointing to mlb_discovery as the source of valid group/type/year values and clarifying that year is a comparison start year whose output includes yearly values and differences.

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?

The description states a specific verb and resource (returns Baseball Savant Year-to-Year Changes tables) and enumerates the four group scopes (batters, pitchers, batting teams, pitching teams). An agent can immediately tell this is a year-over-year comparison table tool rather than a single-season stat tool.

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?

It explicitly routes value discovery to 'mlb_discovery for all accepted group, type, and year values,' which is actionable guidance. It does not, however, state when to prefer this tool over other statcast siblings, so it stops short of full when/when-not coverage.

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