create_view

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

With no annotations provided, the description fully discloses key behaviors: select_body is executed as DDL, the guard is always on and fail-closed, and specific keywords are rejected even inside literals. This equips the agent to handle the tool safely.

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 purpose line, caution, detailed constraints, and argument descriptions. However, the argument descriptions partially repeat the guard mechanism from the caution, introducing slight redundancy. It remains mostly concise and front-loaded.

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 existence of an output schema, return values don't need description. The description covers the creation action, the critical guard, and parameter details. It lacks explicit error handling or prerequisites (e.g., workspace/item must exist), but these are secondary for an AI agent. Overall, it is sufficiently complete.

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?

Despite 0% schema description coverage, the description compensates by providing clear explanations for each parameter: workspace (name or GUID), item (warehouse or SQL endpoint), qualified_name (dot-separated view name), and select_body (with constraints). This adds significant meaning 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 'Create a new SQL view.' as the first line, specifying the verb (create) and resource (SQL view). This distinguishes it from sibling tools like drop_view, update_view, or read_view.

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 explicit warnings about executing select_body verbatim as DDL, specifies that it must be a single read-only SELECT or WITH statement, and details the guard mechanism that rejects write keywords and semicolons. It also gives guidance on rewriting legitimate bodies that contain write keywords.

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