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

Annotations only include idempotentHint: false, leaving the description to carry the full behavioral burden. The description excellently discloses that items are copied, edits to one bank do not affect the other, template support, project scoping rules, and a caveat about referencing banks from Riddles. This goes well beyond the annotation and provides substantial transparency about side effects and constraints.

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 effectively three sentences, each carrying valuable information without fluff. Although the first sentence is somewhat long, it is well-structured and front-loads the core purpose. The content is appropriately scoped and every clause earns its place, making it easy to parse despite its density.

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 mutation tool with three parameters and no output schema, the description covers essential context: how duplication works, project placement, template compatibility, and a critical cross-referencing caveat. It doesn't delve into every edge case (e.g., behavior with tags or sharing settings), but given the tool's simplicity, the description is sufficiently complete for an agent to use it correctly.

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 100%, so the baseline is 3 per the guidelines. The description adds minor additional context around projectId (e.g., 'the project the API key is scoped to') and questionBankId (e.g., 'existing bank or template'), but these details are already present in the schema descriptions. The description does not introduce significant semantic value beyond the schema.

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 the tool's purpose: 'Duplicates a question bank and every one of its items into a new, independent bank.' It uses a specific verb (duplicates) and resource (question bank), and distinguishes itself from sibling questionBank_create by emphasizing the duplication of items and independence of the copy. It also clarifies it works on templates, further disambiguating from other tools.

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 clear context on when to use the tool, such as duplicating banks with items and working with templates. It explains project placement behavior ('project given as projectId, or in the project the API key is scoped to'). However, it doesn't explicitly mention when not to use it or name alternatives, though the context strongly implies its use case.

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