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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds the non-obvious cost signal ('Costs 5 credits') and the per-source historical coverage limits, both of which affect whether an agent should call it. It does not mention pagination behavior beyond the schema's limit, but the credit cost and coverage constraints are the material extras.

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?

Front-loaded with purpose, then the two metric families, then the how-to and the cost — a sensible order with no filler sentences. The metric enumerations are long but each names real, otherwise-unknowable content, so they earn their space; slightly denser than needed for selection alone.

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, return shape needn't be described, and the description covers purpose, coverage years, filter dimensions, and credit cost. The only gap is that it never states the consequence of an out-of-range season for a given source (e.g. PFR before 2018), which an agent may need to avoid wasted calls.

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%, including enum values, the week-0 season-aggregate note, and the per-source player ID convention, so the schema already does the heavy lifting. The description only restates that a source must be picked and that season/week/player/team are the filters, adding nothing beyond the structured fields.

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 (advanced/NGS and PFR metrics) and enumerates the actual metric families it returns (time to throw, air yards, pressures, missed tackles), which is far more specific than the name alone. The phrase 'the box score does not carry' implicitly positions it against the box-score siblings get_player_stats/get_team_stats, so an agent can tell what it adds.

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 explicit coverage windows (NGS 2016+, PFR 2018+) and a clear procedure: 'Pick a source, then filter by season, week, player or team.' It doesn't explicitly name the alternative tool (e.g. use get_player_stats for standard box-score stats) or state exclusions, so it is clear context without hard routing.

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