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

Annotations already declare a safe, idempotent read, so the description's added value is the live-data disclosure: the current round is updated hole by hole as each is marked, which tells the agent the data is fresh. It also adds a behavioral constraint (never tell the user to check the app or that data doesn't sync), which is genuine context beyond the annotations, though it doesn't mention pagination, empty states, or what a missing current round looks like.

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?

Front-loaded with what the tool returns, then when to use it, then the behavioral caveat; every sentence carries information. Slightly dense and parenthetical, but no 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?

With only two optional parameters, full schema coverage and no output schema, the description covers purpose, live-data semantics and the key response constraint. What is missing is minor: no hint about the shape of the returned card or what happens when there is no current round.

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%, and the schema itself already documents the which enum values and that round_id overrides which. The description only loosely restates the current-vs-recent distinction ('la que está jugando AHORA ... o sus últimas vueltas') without adding format or usage detail the schema lacks, so the baseline 3 applies.

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 concrete verb+resource ('Tarjeta hoyo a hoyo de una vuelta') and scopes it to the round being played live or the player's recent rounds, so an agent knows exactly what it returns. It does not, however, differentiate itself from close siblings such as get_round_history, get_scorecard_stats or get_round_shots, which an agent must disambiguate on its own.

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?

Gives explicit invocation triggers — when the user asks to see their round, how it's going, what they shot, or strokes on a hole — which covers the common phrasings. It stops short of naming alternatives or exclusions among the many round-related siblings, and the closing instruction about not redirecting to the app is response guidance rather than tool-selection guidance.

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