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

Beyond the readOnly/destructive annotations it discloses real behavior: due reviews are ordered before new words, new words are capped per dictionary per day by the New/day setting, nextDueAt indicates when scheduled review resumes, and the agent must not reveal the answer before the user replies. That is substantive operational context the annotations cannot carry.

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 use case, then sequencing, then behavioral constraints. It is on the long side and the sentence about answering which languages the user is learning partially restates the earlier no-pair behavior, but nearly every sentence carries actionable content.

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?

For a 4-parameter tool with no output schema, the description covers the call sequence, fallback mode, and references the key return fields (dueTotal, nextDueAt). It stops short of describing the word list shape itself, but an agent has enough to call and interpret the result correctly.

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 the description compensates for the unlabeled 'limit' by clarifying the pair semantics: 'term' is always learningLanguage and 'translation' is translationLanguage, and either quiz direction uses the same dictionary. The mode semantics are largely duplicated from the schema, but the pair-direction rule adds genuine meaning not present in 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 names a specific resource (due vocabulary words / dictionaries) and spells out both operating modes: called without a pair it enumerates dictionaries and word counts, called with a pair it returns the words due. It is clearly distinguishable from siblings like record_review and search_vocabulary.

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?

It gives explicit triggers ('when the user wants to review, practise or be quizzed'), a required call sequence (call without a pair first, then with the pair), a fallback path (use mode 'all' instead of switching dictionaries when dueTotal is 0), and a follow-up route to record_review. Nothing about when to pick this tool is left to inference.

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