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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety is covered. The description adds two genuinely useful behavioral facts not in the structured fields: the cost ("Costs 2 credits") and the data provenance ("computed from every final game"), which tells the agent the numbers are final-game aggregates only.

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?

Two compact clauses with the usage trigger front-loaded and no filler. The metric list is long but each item is a concrete returned field rather than prose padding.

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?

Output schema exists and annotations cover safety, so the description only needs to add cost and scope, which it does. Minor gaps remain: it does not say whether playoff games are excluded from the aggregates, or whether all listed metrics apply to both leagues.

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% with defaults and an enum on league, so the schema carries the parameter burden. The description adds nothing beyond the schema about league/season semantics (e.g., how NCAA baseball standings differ). 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 resource (a season's regular-season standings) and enumerates exactly which metrics are returned (record, home/away, last 10, runs scored/allowed, run differential, Pythagorean win %), which separates it from generic siblings like get_team_stats. It stops short of naming a sibling it is not, so an agent still has to infer the boundary with get_team_stats and get_ratings.

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?

"Use for a season's regular-season standings" is an explicit use trigger and "computed from every final game" implies the source scope. However, there is no when-not guidance, no named alternative among the ~20 siblings, and no guidance on choosing league or season values.

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