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

Annotations already declare readOnlyHint/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond annotations: a 30-minute data refresh cadence and a full accounting of the computed fields (changepoint flag, consecutive-below-normal starts, reasons), which tells the agent how fresh and how derived the output is.

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?

Purpose is front-loaded and the long metric enumeration is dense rather than padded, with the refresh cadence saved for the end. It is somewhat list-heavy, but every clause adds signal about the returned data.

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 no output schema, the description carries the burden of describing return values, and it does so thoroughly, plus it discloses data freshness. Nothing critical is missing for correct invocation, though it could note filtering/pagination semantics for the limit parameter.

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 already documents all five parameters including the red/yellow/green enum and the starting_today default. The description adds marginal meaning (what 'flag level' represents) but does not extend parameter syntax or behavior, so the 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 and resource (pitcher health check) and enumerates the exact metrics returned: velocity, z-scores, spin/release drift, changepoint flag, trend, flag level, bet angles. It is clearly a velocity/health tool, but it never distinguishes itself from the close sibling invoke_mlb_pitcher_splits, so it stops short of a 5.

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?

The description implies usage by specifying 'starting pitcher health check for today' and the schema default starting_today=true, so the agent can infer when it applies. However, there is no explicit when-to-use/when-not guidance and no pointer to alternatives such as pitcher_splits or starters, leaving routing to inference.

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