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

Annotations are all false, so the description carries the burden. It discloses the write nature ('Saves'), the effect of each rating ('unknown' sends word back to start), and the return value (new box 0-4 and next due date). It does not explicitly mention idempotency or error scenarios, but the directive to call once implies non-idempotency. This is solid transparency beyond the annotations.

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 longer than ideal but every sentence carries purpose: main action, timing, special case (practice), rating definitions, and return info. It is front-loaded with the core purpose and well-organized, avoiding redundancy.

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 tool's write nature and single parameter, the description covers when to call, what to pass, how to rate, and what to expect in return. It lacks explicit mention of error handling, rate limits, or prerequisites (e.g., word must exist), but these are not critical for correct invocation. The output is described sufficiently despite no output schema.

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?

The schema defines the 'reviews' array but gives no semantics for the rating values. The description adds critical meaning: 'known' requires recall without a hint, 'unknown' sends the word back to the start. It also implies the 'id' is the word identifier via 'every word asked.' This compensates for the 0% schema coverage on semantic meaning.

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 clearly states the action: 'Saves a quiz round to the user's spaced-repetition schedule.' It specifies the resource (quiz round) and the destination (schedule), and it establishes the tool's role as the only one that records review results, distinguishing it from siblings like save_deck or list_due_words.

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 timing instructions: 'Call once at the end of every round with every word asked, not after each word.' It also clarifies that practice rounds (mode 'all') must be recorded, and the instruction 'never offer a round that is not recorded' reinforces when the tool is required. Rating semantics are explained with concrete criteria for 'known' vs 'unknown'.

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