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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds substantive domain behavior beyond that: bust rules, ignored darts after a finish, double-out requirements, and what the response includes (remaining, per-turn detail, busts, average, checkout suggestion, CSV). This is unusually complete behavioral disclosure.

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 intent examples, then rules, then exclusions. Despite covering several important constraints, every sentence contributes directly to correct invocation or scoping.

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 an output schema present, the description need not explain return shape in detail, but it still summarizes important outputs. Combined with 100% schema coverage and clear annotations, an agent has everything needed to call the tool correctly and understand its behavioral limits.

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 start, turns, darts, and double_out are already documented in the schema. The description reinforces the turn grouping and dart formats, but mostly restates schema-level details rather than adding new parameter semantics, making the baseline 3 appropriate.

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 ('score a 501 or 301 darts leg') and immediately distinguishes the scope with concrete user phrasings. It also explicitly rules out cricket and around-the-clock variants, so the agent can separate this from unrelated siblings like score_dice_sheet and show_scoreboard.

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?

Provides explicit when-to-use examples and clear exclusions: not for cricket or around-the-clock, and not for multi-leg matches. It also states the one-leg-per-call constraint, leaving little ambiguity about when to invoke it versus not.

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