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

Annotations already mark it read-only and idempotent, and the description adds substantial non-obvious behavior: it returns the raw box-score archive including games no sportsbook priced, carries no line/price/grade, applies limit after the opponent filter, and explains that team fields are null for individual sports. No contradiction with annotations.

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 dense but well-ordered: core purpose first, then semantic details, important caveats, and final null-field guidance. Every sentence contributes meaning and the tool is not padded with filler.

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?

Even without an output schema, it explains what the response contains, what it does not contain (lines, prices, grades), how H2H scoping behaves, and how to handle unknown team/null values. This is complete enough for an agent to call the tool correctly and reason about the returned stats.

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?

Despite 80% schema coverage, the description adds real value beyond schema: opponent accepts full names, nicknames, or abbreviations; limit is applied after H2H filtering; and player_name must match box score formatting. This gives the agent practical guidance that the schema alone does not provide.

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 states a specific verb and resource: it returns a player's recent games with every raw box-score stat per game. It also distinguishes itself from propline_get_player_trends and clearly mentions the H2H use case, so an agent can tell it apart from very similar siblings.

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?

Explicitly says when to use it ('how has X actually performed lately?', build L5/L10/L20/season splits/H2H yourself) and when not to: use propline_get_player_trends for hit rates against a posted line. It also calls out the important caveat that unpriced games are included and H2H is not limited to the current season.

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