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

Annotations already establish this is a safe read (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description still adds real behavioral context: model scope (regular season since 2022-23), freshness (updated daily in season), and an accuracy backtest (3.71 vs 4.41 baseline). It omits any return/format or pagination behavior, but that gap is minor given the annotation coverage.

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?

It is front-loaded with the metric definition before moving to views and provenance, and most sentences carry load-bearing information about the data model. It is somewhat dense and includes promotional/backtest material that is not strictly needed to call the tool, but nothing is truly wasted.

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?

For a 10-parameter read tool with no output schema, the description defines the returned metrics, the archetype categories, freshness, and model scope, which is most of what an agent needs. Return shape and pagination handling are left to the schema, which is acceptable given there is no output schema to lean on.

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 70%, so the schema already documents most fields. The description earns extra credit by expanding the view enum with real meaning (systems = team lift for latest season; step_up = gains when the star sits over 5+ games) and by noting the player param accepts part of a name, which goes beyond the terse schema strings.

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 (NBA Player Index) and verb-level detail: it decomposes DK points per 36 into player_value, system_lift and teammate_drag. It also explicitly distinguishes itself from the nearest sibling by declaring it is 'a ranking of who is real and who rides the team, not a nightly projection,' which separates it from invoke_nba_projections.

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?

It enumerates the three views and when each applies: players (default; pass player for a single player's season history), systems (team lift, latest season), and step_up (biggest gains when the star sits, 5+ games). That is clear context for selecting a mode, but it never names an alternative tool to use instead, so exclusions are implied rather than explicit.

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