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

With only idempotentHint=false in annotations, the description carries most of the behavioral burden and does so well. It discloses that the bank is created empty, that its riddle type is fixed for the lifetime of the bank, and that the bank is scoped to a single project with fallback behavior when projectId is omitted. It does not mention permissions or error conditions, but the core behavior is transparent.

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 dense but efficient: every sentence earns its place. It front-loads the primary purpose, then explains the follow-up workflow, type restriction, and project scoping. Despite its length, there is no fluff or repetition of annotation data.

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 tool has no output schema, so mentioning the returned 'id' is important and the description does that. It also covers the lifecycle context (add items, reference the bank from a matching Riddle, project restriction), making it usable without further documentation. A fuller description might specify the exact response shape, but it is not necessary for correct invocation.

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 input schema already documents all three parameters with 100% coverage, so the baseline is 3. The description adds meaningful semantics beyond the schema, especially the project/Riddle coupling: pass the projectId of the project the Riddle belongs to, and omitting it creates the bank in the project scoped to the API key. This strengthens parameter understanding beyond field definitions.

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 opens with a specific verb and resource: 'Creates a new, empty question bank for the given Riddle type ("Quiz" or "Poll").' It clearly distinguishes this creation tool from sibling questionBank_* tools that add, list, update, or delete banks.

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 a clear workflow: create the bank, add items with questionBank_addItem, then use the returned id as questionBankId on a matching question-bank block. It also states exclusions, such as a quiz bank never being usable for a poll, and explains the projectId requirement. It lacks an explicit 'when not to use' statement but the usage context is strong.

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