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

Annotations already establish readOnly/openWorld/non-destructive, and the description adds real behavioral substance on top: data provenance (official injury report), the historical window (last two seasons), that every row carries a sample size, that questionable players branch into plays/sits paths, and the explicit limitation "Historical splits only, no projection." The only missing pieces are ordering, row count, and cost/pagination behavior.

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?

The trigger examples are front-loaded and nearly every clause carries information (data source, stat basis, sample size, branching, no-projection caveat). The middle portion is a dense run-on that lists five stats and three output elements in one breath, which costs a little scanability.

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 and four all-optional parameters, the description carries the burden of return-value description and does so at a useful level: ranked teammates with per-stat splits, sample sizes, and Kalshi prices side by side. Missing is what happens with zero absences or an unmatched player name, which matters given that every parameter is optional.

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%, so the baseline is 3; the description goes slightly beyond by framing what the parameters drive — you can ask about a specific absent player or a teammate, and beneficiaries are ranked by stat with points as the cited default. It does not clarify how game/team/player interact when several are supplied, so it does not fully escape the baseline.

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 concrete resource (today's NBA absences from the official injury report) and the value-add layer (teammates whose minutes/points/rebounds/assists/usage rose without the star), reinforced by two real user-phrased examples. That is far more specific than the name alone. It stops short of a 5 because it does not explicitly separate itself from nba_prop_board, which also surfaces prop prices, so the boundary is left implicit.

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 "Embiid's out tonight — who benefits?" and "who's out in the NBA today"" gives clear, quotable trigger conditions for two distinct query shapes. There is no when-not-to-use guidance and no pointer to nba_prop_board or calculate_ev for follow-on pricing questions, so routing is stated but not exclusive.

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