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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds useful behavioral context beyond that: the exact payload changes by mode, the breadth of returned fields, and the 'refreshes every 30 minutes' data-currency note.

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 sentences, front-loaded with the tool's identity, then mode behavior, then refresh cadence. Dense field enumerations make it long, but each clause carries information an agent needs to predict the response shape.

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?

There is no output schema, so the description carries the full burden of describing returns, and it does so thoroughly for both modes (hand, implied runs, K props, splits, lineup order, matchup scores, park HR index). An agent can predict the response without guessing.

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 the schema documents team, pitcher, and limit on its own, setting a baseline of 3. The description adds real meaning by spelling out how the presence or absence of pitcher/team toggles between list mode and full-lineup detail mode.

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?

The description names a specific verb+resource ('starting pitcher vs opposing lineup matchups') and precisely scopes it to 'Today's' MLB slate. It does not explicitly name or contrast with siblings such as invoke_mlb_pitcher_splits or invoke_mlb_hitter_splits, which it partially overlaps, so an agent must infer differentiation from content alone.

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?

It clearly explains the two invocation modes: 'Without pitcher or team it lists every starter...' versus 'With pitcher or team it adds the opposing lineup...'. That is genuine when-to-use guidance for the parameters, though it offers no exclusions or pointers to alternative tools for narrower needs.

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