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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint, covering safety. The description adds genuine behavioral context beyond that: 'Tennis-only', season default, tour optionality for a combined board, a minimum 10-decider qualification, parallel-safe status, and upstream cost. This helps an agent reason about cost and data filtering beyond the basic read-only profile.

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 front-loaded with the essential definition, then organized into clear usage blocks (When to use, Do not use, defaults). It is slightly bloated by repeating the same 'Share of deciding sets...' phrasing in both the opener and the 'When to use' bullet, but overall every section earns its place and guidance is easy to scan.

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 leaderboard tool with an output schema and strong annotations, the description covers all necessary context: game restriction, season default, tour behavior, minimum match qualification, throughput safety, and alternative tool routing. An agent has everything needed to correctly select and invoke this tool.

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 description coverage is 100%, so the baseline is fair. The description doesn't add much beyond the schema: it repeats the season default and tour optional/combined-board behavior that already appear in parameter descriptions. The only extra is the minimum 10-decider threshold, which is not parameter-specific but a data filter. It doesn't materially de-risk parameter choice beyond the schema.

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 opens with a highly specific purpose: a tennis season leaderboard for share of deciding sets won, from real match rows, ordered by percentage. It distinguishes itself from sibling leaderboards like leaderboard_tiebreak_win_pct and leaderboard_break_points_saved by name and metric, so an agent can tell which leaderboard to pick without opening schemas.

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?

The description provides a dedicated 'When to use' block, names an alternative ('raw leaderboard via call_api') and explicitly states 'Do not use when' with concrete alternative mappings (standings, rankings_movers, player_form). This is exactly the kind of when/when-not/exclusion guidance the dimension asks for.

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