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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds a real behavioral trait beyond that: each Batter/Pitcher (and window) group is sorted and paginated independently, which materially affects how limit/offset behave. It stops short of describing return shape, though an output schema exists to cover that.

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

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

Three tight sentences, front-loaded with what it fetches, then the selection dimensions, then routing hints. No filler, and the most decision-relevant constraint (independent group pagination) comes before the alternatives.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and full annotation coverage, the description needn't explain return values. It covers selection dimensions and the independent-group pagination gotcha, which is the main risk for this tool. Minor gap: it doesn't clarify the 0-500 offset-per-group interaction with the 1-500 limit, but that is largely schema territory.

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

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

Schema description coverage is 100%, so all five parameters (role, limit, metric, offset, window_pa) are already documented with defaults and ranges. The description restates metric/role/window values and adds the per-group pagination framing, but adds little syntactic meaning beyond the schema. Baseline 3 applies.

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

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

States a specific verb ('Fetch') and resource ('Baseball Savant Rolling Windows rows for batters and pitchers'), and distinguishes itself from siblings by naming mlb_discovery for exact values and noting that player rolling-breakdown charts are a separate tool. An agent can tell it apart from the many mlb_statcast_* siblings without opening any schema.

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

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

Gives clear routing context: use mlb_discovery for exact metric/window values, and player rolling-breakdown charts live elsewhere. It does not state explicit exclusions (e.g., what this is not for beyond charts), but the pointer to mlb_discovery for value enumeration is genuinely actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.