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

The description goes beyond the readOnlyHint annotation by disclosing the non-obvious requirement to read distractor reasons even after a correct answer. It also reveals the pedagogical rationale that knowing why the tempting option was tempting is the part that transfers. This gives an agent useful behavioral expectations beyond the structured 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 front-loaded with the core purpose and output, followed by a behavioral instruction and a concise delegation rationale. Every sentence earns its place, and there is no redundant restating of the title or schema.

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 simplicity, fully documented parameters, and annotations, the description is complete. It explains what the tool returns, how the result should be used pedagogically, and where the underlying content comes from, so an agent has enough context to invoke it 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?

The input schema already fully documents both parameters: 'id' as an item id from a draw response and 'choice' as a zero-based option index. The description adds no additional parameter-level meaning, so the baseline score of 3 applies.

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 identifies the verb (mark/check) and resource (a vocabulary answer), and specifies exactly what the tool returns: correctness, the correct option, why it fits, and why every distractor fails. It also distinguishes itself from siblings by emphasizing the curated human-written Words in Context question bank and the direct-call option.

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 provides clear usage context: it is for checking a vocabulary attempt and delivering teaching content, including reading distractor reasons even when the answer is right. It also explains why delegation is appropriate, citing the curated question bank and the danger of generated questions with two defensible answers. It does not explicitly contrast with vocab_draw, but the sibling relationship and 'id from a draw response' make the intended flow clear.

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