create_questions

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

The annotations only say the tool is not read-only, not idempotent, and not destructve — they carry no behavioral detail. The description adds substantial disclosure: batch semantics, service-assigned `order` being rejected, `is_graded`/`is_optional`/`answer_feedback_html` being rejected, and the surprising FITB behavior that every answer sent is stored as correct. These are exactly the kind of server-side behaviors an agent cannot infer.

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?

Every sentence carries call-correctness information that the otherwise-empty schema omits; there is no filler or boilerplate. The structure — purpose, parent rule, lifecycle, per-type table, answer shape, rejected fields, permissions — is logical and uses heavy formatting to aid parsing. It is long, but the length is justified by 0% schema coverage.

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 an empty schema and minimal annotations, the description covers the full call-shaping surface: required fields, parent exclusivity, per-type rules, limits, rejected fields, and permissions. The main residual gap is batch failure semantics — whether one invalid item fails the whole batch or is skipped — which matters for retrying a large create. The presence of an output schema reasonably covers return-value expectations.

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 description coverage is 0% and the sole `questions` parameter is an opaque array with additionalProperties: true — the schema provides zero meaning. The description fully compensates: it defines required per-item fields (question_html, question_type, exactly one parent), the answer shape {answer_text, correct}, the answer_text length limit, and per-type answer constraints.

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 opening line 'Create one or more questions' states a specific verb and resource, and the explicit 'BATCH operation' marker distinguishes it from singular create/update tools. The create verb cleanly separates it from sibling list_questions, get_question, update_questions, and delete_questions without needing to open their schemas.

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 gives clear guidance on the central usage decision — exactly one parent, quiz_id vs question_bank_id — with lifecycle consequences explained ('a question in a bank is reusable across quizzes; a question in a quiz belongs to it alone and is deleted with it'). It also states the required permission scopes. It does not explicitly name alternative tools or exclusion conditions, but for a create tool the parent choice is the key routing decision.

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