lakehouse_load_table

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the call is long-running, which should set agent expectations for an async operation, and flags the schema-enabled lakehouse incompatibility as a hard constraint. However, it does not mention that the 'Overwrite' mode replaces existing table data — a destructive behavior worth surfacing given destructiveHint=false. No contradiction with the annotations.

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?

Two sentences with zero waste: purpose and the long-running warning are front-loaded, and the exclusion with alternative follows immediately in the second sentence. Every clause 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 7-parameter mutation tool with a nested formatOptions object and no output schema, the description covers the key non-obvious constraints (long-running behavior, schema-enabled incompatibility) and the schema documents all parameters. The notable gap is that a long-running load likely returns a job or operation identifier requiring status tracking, which is not mentioned so an agent won't know how to poll for completion.

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%, with every property (mode, pathType, tableName, lakehouseId, workspaceId, relativePath, formatOptions) already documented in the schema. The description only adds marginal meaning by linking 'file path' to relativePath/pathType. Baseline 3 is appropriate since the schema does the heavy lifting.

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?

States a specific action (load data), target (lakehouse table), and source (file path), and immediately distinguishes the tool with a long-running caveat and an explicit exclusion for schema-enabled lakehouses. This differentiates it from siblings like lakehouse_list_tables, lakehouse_create_shortcut, and sql_endpoint_execute_query without opening their schemas.

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 explicit when-not-to-use guidance ('Not supported for schema-enabled lakehouses') and names concrete alternatives ('use sql_endpoint_execute_query with COPY INTO or notebooks instead'). The when-to-use case is clear from the purpose: loading a file-path source into a lakehouse table. Nothing 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.