generate_code

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

Annotations already declare readOnlyHint and idempotentHint, so no side-effect warning is required. The description adds substantial behavioral detail beyond annotations: REST code covers token issuance through response determination, realtime code uses websocket subscription, and order/exchange code includes a confirm=True safety gate before transmission.

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?

Four short Korean sentences front-load the core purpose and pack conditional behavior without repetition or filler. Each sentence adds a distinct piece of information: main action, REST/realtime variation, safety mechanism, and token-only mode.

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 one-parameter code generator with an output schema and safety annotations, the description covers the main generation modes and the confirm safeguard. The notable gap is that exact api_type values are not specified, and no pointer to sibling conventions or an enum is provided, so an agent may not reliably know which literal to pass.

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 schema provides only a bare string api_type with no description or enum, and schema coverage is 0%, so the description must compensate. It explains behavior for REST, realtime, order/exchange, and token, and even quotes api_type='token', but it never enumerates the exact accepted literal values or formats, leaving ambiguity about what string to pass for non-token modes.

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 precise verb-object statement: it creates Python code that calls the given api_type, then immediately distinguishes REST, realtime, and token modes. This clearly separates it from sibling tools like search_api and get_api_detail, which focus on API discovery rather than code generation.

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 context for how behavior changes by api_type (REST, realtime, order/exchange, token), which guides parameter choice. However, it never explicitly names sibling tools or states when to prefer this tool over list_categories, search_api, or get_api_detail, so alternative routing is left to inference.

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