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

Annotations already declare read-only, idempotent and non-destructive, and the description adds behavior annotations do not carry: generation must be blocked until inputs are confirmed, the response must be presented in full rather than summarized, and winners are not recorded. These are real constraints on how the agent runs the call, not restatements of the annotation flags.

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 the mandatory precondition block before the capability description, and every sentence carries a rule. Some redundancy exists between the 'never infer' sentence and the 'requires clarification, not an Americano' example, keeping it just short of ideal.

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 no output schema, the description correctly states that every returned match with round, court and time must be shown. It covers the highest-risk ambiguity (unconfirmed sport/format) and scope limits. It does not explain how byes are derived from count or how courts constrain scheduling, but those gaps are modest for a read-only computed 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 coverage is 75% and already documents seed repetition, names vs. numbered placeholders, and time format. The description adds meaning the schema lacks: sport must be user-confirmed rather than inferred, and individuals vs. fixed teams should be clarified when ambiguous. It leaves court-count and duration semantics to the schema, which mostly handles them.

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 specific verb and resource: a pickleball seeded or random single-elimination bracket with byes, court assignments and provisional times. It also names what it is not (no winners recorded, no saved event, no double elimination), which separates it from the round-robin, Americano and Mexicano 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?

Explicit preconditions: sport and format must both be confirmed for this tournament, otherwise ask or call get_supported_tournament_options. It names the alternative tool, forbids inferring from prior conversation or player/court counts, and gives a concrete disambiguation example ('20 players on four courts').

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