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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, and the description adds useful output shape (exactly 5 questions, 4-6 rankable items each). However it never says what is persisted or returned — whether a quiz object is created, an id comes back, or how AI-generation failures behave — which matters for a mutating generation tool.

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?

Three sentences, front-loaded with the action and the mode split, followed by output shape and a closing restatement of the two modes. Nothing is padded; each sentence carries distinct information.

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 13-parameter, zero-required-parameter tool with two mutually exclusive modes, the description gives the mode logic, conditional requirement, and output shape. It omits what happens when neither unit_id nor sources are supplied with auto_research=false, and whether course_id is required for the completion tracking it hints at.

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 100%, so baseline is 3, but the description adds real grouping semantics: it maps the long parameter list into two coherent modes and flags title as conditional on source mode. It also mentions the ranking criteria dimension (chronological, size, importance), which has no corresponding parameter and is purely behavioral context.

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?

States a specific verb and resource ("Generate 5 AI-powered ranking questions") and immediately names the two input modes (unit_id vs. custom sources). The resource is clearly distinct from siblings like create_mcq, create_flashcards, or create_quiz, so an agent can route without opening the schema.

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?

Explicitly frames the either/or decision ("existing unit (unit_id) or custom sources") and notes title is required in source mode, which is the key branch an agent must resolve. It stops short of naming alternatives such as edit_ranking for modifying an existing one, or when ranking beats create_quiz.

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