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

Annotations already declare read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description adds that ratings are a ranking tool rather than projection input and defines the two track metrics, but it omits return format, pagination behavior, and any access constraints.

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 description is three front-loaded sentences covering dataset identity, metric meanings, and a key caveat. It is efficient, though the metric sentence is slightly fragmentary and could be clearer.

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 read-only dataset tool with no output schema, the description sufficiently explains the content categories returned: player ratings, team offense, team defense, and tracked metrics. It does not detail exact row structure, but annotations and schema handle safety and filters.

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?

The schema documents team, limit, and position, while the description adds meaning for the group values by describing players, offense, and defense outputs. It also explains the track enum by defining fpts as DK points and eff as points per opportunity, which compensates for the 60% schema description coverage.

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 identifies a specific dataset: NFL Elo ratings covering individual player ratings by position, team offense units, and team defense by position. It also implicitly distinguishes from projection tools by stating ratings are a ranking tool, not a projection input, though it does not name a specific sibling alternative.

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 provides one useful exclusion: ratings are not a projection input, which implies a ranking use case. However, it does not explicitly say when to choose this tool over siblings such as invoke_nfl_projections or invoke_nfl_player_pool.

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