get_quiz_attempts

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

With no annotations, the description carries the transparency burden but largely mirrors schema details: the default status is already in the schema, and include_review's heavier nature is also described in the schema. It adds minimal new context beyond confirming read-only behavior via the tool name.

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 two short sentences that front-load the core purpose and essential usage note, with no wasted words.

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?

The description covers the main purpose, default behavior, and a critical performance caveat, which is sufficient for a retrieval tool. It omits details like status enum values and return format, but these are available in the 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 has only 25% coverage (include_review). The description compensates by clarifying that quiz_id and user_id target a specific user on a quiz, and it explains the status default and include_review behavior, making the tool usable without reading 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 clearly identifies the resource (quiz attempts), the scope (a user on a given quiz), and implies the 'get' action via the tool name. It distinguishes from siblings like get_quiz_questions (questions) and get_grades (grades) by focusing specifically on attempts.

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 explains the default behavior (finished attempts) and when to use include_review for per-question details, noting the heavier cost. However, it does not explicitly reference alternative tools or mention when not to use this tool.

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