create_card

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

With no annotations, the description carries full burden. It states the tool creates a card and returns the created object, implying a write operation. However, it does not disclose potential side effects (e.g., duplicate name handling), required permissions, or idempotency. Some transparency exists but gaps remain.

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 well-structured with a clear header, parameter list, and return statement. Each parameter gets its own line for readability. However, the parameter lines are somewhat repetitive ('Args:' prefix), and could be more concise without losing clarity.

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 output schema exists, the description does not need to detail return values beyond noting it returns the card object. It covers all required and optional parameters with brief explanations. However, it does not specify constraints like valid SQL format or database_id existence checks, leaving some questions for a complete agent.

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 0%, so description must compensate. It lists all 6 parameters with brief explanations, adding meaning beyond the schema's type definitions. However, some explanations are tautological (e.g., 'name: Name of the card.'), and for complex fields like visualization_settings, no additional format guidance is given, limiting depth.

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 'Create a new question/card in Metabase.' with a specific verb and resource. It lists all parameters and their roles, and distinguishes from sibling tools like create_model or create_dashboard by focusing on 'card'. The name and description together make the tool's purpose unambiguous.

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 no guidance on when to use this tool versus alternatives like create_mongodb_card or create_model. It does not mention prerequisites, error conditions, or contexts where this tool is preferred. The only instructions are parameter explanations.

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