lakehouse_create_shortcut

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

Annotations (readOnlyHint=false, destructiveHint=false) are consistent with 'Create' — no contradiction. The description adds value beyond annotations by disclosing that schema shortcuts 'import all Delta tables from the target as a new schema' and flagging that schema-enabled lakehouses are in preview. It does not discuss conflict-overwrite side effects, but shortcutConflictPolicy in the schema covers that behavior.

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 sentences with no filler; the core action is front-loaded, followed by the two key usage patterns and a target-type summary. The target enumeration slightly duplicates the schema's target object descriptions, but as a scannable quick reference it earns its place for a tool with an 8-variant nested target.

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 complex tool with 6 parameters, an 8-variant nested target object, and no output schema, the description covers the nuanced decision points (schema vs table shortcuts, path conventions, supported targets) and the schema fills in all parameter details at 100% coverage. Minor gap: no mention of what the operation returns on success, but nothing an agent needs to call it correctly is missing.

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%, setting the baseline at 3. The description earns above baseline by explaining the semantic combination of path and name (path='Tables' + name makes a schema shortcut; path='Tables/<schemaName>' makes a table shortcut) and enumerating valid target types. It adds relational meaning the per-property schema descriptions do not fully convey on their own.

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 first sentence states a specific verb (create), resource (OneLake shortcut in a lakehouse), and scope (any level: file, folder, table, or schema). It clearly differentiates from sibling tools like lakehouse_create (creates a lakehouse itself) and lakehouse_list/get/delete_shortcut (read/delete operations), so an agent can select it unambiguously.

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?

Provides concrete scenario-based guidance: how to configure a schema shortcut (path='Tables' + name=schema name) versus a table-level shortcut (path='Tables/<schemaName>'), plus the full list of supported target types. It does not explicitly name excluded alternatives, but no sibling competes for this operation, and the scenario routing is actionable and precise.

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