clone_table

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

With no annotations provided, the description carries full responsibility for disclosing behavioral traits. It clearly states the clone is 'zero-copy' and explains the point-in-time behavior with retention window. However, it omits details like required permissions, whether the operation is reversible, or if there are side effects on the source table.

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 concise: one sentence for purpose, one line for restriction, then a bulleted Arg list. No unnecessary words. Front-loaded with the most critical info. Every sentence earns its place.

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 tool with 5 parameters (4 required), an output schema exists, and no enums/nested objects, the description covers the core functionality, constraint, and parameter details. It does not mention the return value, but the output schema handles that. One could argue it could note that the operation only works on Fabric Warehouses (already done) and perhaps hint at alternatives for other platforms, but it's largely 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?

Schema coverage is 0%, so the description must fully explain each parameter. The Args section does this excellently: it clarifies that 'source' must be a qualified name, provides an example for 'at' (ISO-8601 format with a concrete timestamp), and explains the default behavior when 'at' is omitted. This adds substantial meaning beyond the bare JSON 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 action ('Create a zero-copy clone of a table') and the SQL command used, distinguishing it from siblings like 'create_table' which would create a full copy. The specific verb 'clone' plus resource 'table' leaves no ambiguity about the tool's purpose.

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 explicitly restricts usage to 'Fabric Data Warehouses (not SQL Analytics Endpoints)', providing a clear when-not condition. It also explains the optional 'at' parameter for point-in-time clones. However, it does not explicitly name alternative tools like 'create_table' for full copies, which would strengthen guidance.

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