update_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 destructive. The description goes far beyond that: it discloses partial-update preservation, immutable answers, read-only fields, per-row failure behavior for conflicting flags, and the permission requirement. This is exactly the kind of behavioral context that annotations alone do not provide.

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 detailed but every sentence carries operational value. It is front-loaded with the core purpose and batch nature, then systematically covers preservation semantics, immutability, read-only fields, per-row error handling, and permissions. No filler or redundancy.

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 complexity and the extremely minimal input schema, the description is quite complete: it explains the batch contract, id requirement, partial-update semantics, immutable answers, read-only fields, failure behavior, and auth scope. It does not enumerate every possible question attribute, but the open `additionalProperties` schema plus an output schema makes that less critical. Some guidance on the expected success response shape would fully close the gap.

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 `questions` items allow `additionalProperties: true`, so the schema conveys almost nothing about parameters. The description compensates by stating that each item needs an `id`, that there is no `answers` field, and that certain fields are read-only. It does not enumerate all possible updatable attributes, but for an open-object batch update it covers the most critical constraints an agent must know.

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 states a specific verb and resource: 'Update one or more existing questions.' It also identifies this as a BATCH operation, which differentiates it from single-item update tools and sibling tools like create_questions and delete_questions. The agent knows exactly what the tool does 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?

The description provides strong usage guidance: it explains the batch nature, the need for an `id` per item, the partial-update semantics, and explicitly routes answer changes to `delete_questions` plus create. It also names the required permissions (question-banks:write OR quizzes:write), so an agent can decide whether this tool is appropriate and authorized.

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