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

Annotations already mark this as read-only and non-destructive, and the description adds substantial behavior beyond that: it lists dictionaries with word counts when called without a pair, clarifies that a dictionary is identified by pair not direction, exposes dueTotal and nextDueAt semantics, and describes the interactive expectation of not revealing answers. This is valuable context the structured fields do not provide.

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 long but every sentence earns its place: usage guidance, scoping rules, interactive behavior, and follow-up action are all covered without repetition. It is front-loaded with the primary use case and then expands into needed details, making it easy for an agent to parse.

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 carries the burden of explaining return-like concepts, and it does: dueTotal, nextDueAt, dictionary word counts, and language-pair identification. It also covers the no-pair call flow, the all-mode fallback, and the required follow-up with record_review. An agent has enough information to invoke this tool correctly in the intended scenarios.

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 75%; mode and the language parameters are already described. The description adds meaning by explaining that the same dictionary can be quizzed in either direction, that a dictionary is identified by its pair, and that mode 'all' should be used when dueTotal is zero. Limit is the one parameter not addressed, but it is self-explanatory and constrained by the schema.

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 specific use case: 'review, practise or be quizzed on their NextLang vocabulary.' It clearly identifies the tool's resource (NextLang vocabulary) and differentiates it from sibling tools by stating when to call without a language pair versus with one, and by naming record_review as the follow-up. The distinction between dictionary identity and quiz direction further removes ambiguity.

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 gives explicit when-to-use instructions: call without a pair first, then call with the pair. It even provides a conditional: if dueTotal is 0 and the user wants to practise, call again with mode 'all' instead of switching to another dictionary. It also tells the agent not to reveal answers and to save results with record_review, covering next steps.

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