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

Annotations already declare readOnly, idempotent, non-open-world, non-destructive behavior, so the safety profile is covered. The description adds one genuinely non-structured fact — that the deeper breakdowns (RAPM, on/off) are gated behind Pro — which is real value. It says nothing about result volume, pagination, or whether standings/power rankings cover a full league.

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?

A single front-loaded sentence with no filler; each clause corresponds to one kind value. It is dense but readable, and the parenthetical detail is placed where it disambiguates 'ratings' rather than tacked on at the end.

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 must carry the return-value burden; it does so for 'ratings' but leaves standings and power_rankings undescribed (all teams? current week?). For a read-only tool whose annotations cover safety, this is adequate but incomplete.

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 coverage is 100% with enum values enumerated, so the baseline is 3; the description earns a bump by spelling out what the abstract kind labels actually return (Keel Impact with offense/defense, box prior, RAPM vs. NFL EPA/play and success rate). That mapping helps the agent choose a kind rather than guess from bare enum tokens.

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?

Specific verb ('Get') plus concrete resources: NBA Keel Impact player ratings, NFL EPA/play leaderboards, standings, power rankings. The kind enum maps 1:1 to the sentence's clauses so an agent can tell what each mode returns. It stops short of differentiating from siblings like player_splits_and_on_off, whose 'on/off breakdown' overlaps with the Pro bullet here.

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?

Usage is only implied through the four kind names — nothing tells the agent when to pick this over player_profile, player_splits_and_on_off, or team_profile for related statistics. The 'Pro' note hints at an entitlement requirement but is not framed as a precondition.

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