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

Annotations already declare readOnlyHint, openWorldHint, and non-destructive behavior. The description adds useful behavioral context beyond that: data is from 'real match-stats aggregates,' rows contain aces and matches played, results are ordered most aces first, and the tool is 'Parallel-safe: yes. Upstream cost: 1.' This goes beyond what the annotations alone convey, though it does not address potential staleness or result shape details, which the output schema covers.

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 well-structured with labeled sections ('When to use', 'Prefer over', 'Do not use when') and compact sentences. Every line carries information: scope, defaults, exclusions, parallel-safety, and cost. There is no filler or repetition of schema content.

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?

Given the output schema exists, the description does not need to repeat return structure. It covers the tool's purpose, use cases, exclusions, defaults, ordering behavior, and execution safety. Nothing relevant to selecting or calling this tool correctly is missing.

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 adds meaningful parameter guidance by clarifying that season defaults to 2026 and tour (ATP|WTA) is optional, explicitly instructing to omit it for the combined board. It also reinforces that division is a synonym for tour, matching the standings tool spelling, which helps disambiguate the two interchangeable parameters.

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 precise statement: 'Tennis season aces leaderboard: most aces served in a season, from real match-stats aggregates.' This names the resource (season aces leaderboard), the metric (aces served), and the domain (tennis), making the tool's purpose unambiguous and distinct from sibling leaderboard tools.

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 explicit when-to-use guidance ('Who leads the tour in aces this season'), a preferred alternative ('Prefer over: raw leaderboard via call_api'), and clear exclusions with named alternatives: standings for ranking position, rankings_movers for week-over-week movement, and player_form for recent form. It also states 'Tennis-only' and explains optional tour behavior.

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