ghl_course_upsert_quiz_questions

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

Annotations already declare idempotent=true, readOnly=false, destructive=false, so the safety profile is covered. The description adds real behavioral context beyond that: OAuth scope (courses.write), the mandatory Version: v3 header, sub-account token requirement, and the non-obvious fact that quizId comes from the path rather than the body. It stops short of explaining what happens to questions omitted from the payload, which matters for a 'replace' operation.

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 core operation and the path-vs-body caveat are front-loaded, which is good. There is some low-value metadata (duplicated token requirement, 'source: v3/courses-v3.json', repeated endpoint line) that could be trimmed without losing 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?

Auth, version header, and path parameter semantics are well covered, and the nested body is fully documented by the schema. However, for a tool whose title says 'Replace', the description never explains whether existing questions are deleted or merged, and there is no output schema or description of the response. That ambiguity is a meaningful gap for a mutation tool.

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 the baseline is 3, but the description adds genuine meaning: it clarifies that {productId} is the course/product id (non-obvious naming) and that quizId is taken from the path, not the body. The body's nested question structure is left entirely to the schema, which is reasonable given coverage.

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?

Description states a specific verb and resource ('Batch upsert quiz questions') and pins it to an exact endpoint (PUT /courses/products/{productId}/quizzes/{quizId}/questions), so the agent knows precisely what operation is performed. It does not explicitly differentiate itself from siblings like get_quiz_questions or update_quiz, but the title and endpoint make the distinction inferable.

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?

Usage is implied by 'Replace Quiz Questions' and the write scope, but there is no explicit statement of when to use this versus ghl_course_get_quiz_questions or ghl_course_update_quiz, nor any prerequisites or call-ordering guidance. The auth note ('Requires a Location token with courses.write') is a precondition, not usage guidance.

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