export

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

With no annotations, the description carries the transparency burden. It discloses a critical behavioral trait: 'The destination session and acting identity come from process-level environment variables, never from model-supplied tool arguments.' This goes beyond the generic action and warns against passing identity arguments. However, it does not mention potential side effects like overwriting existing datasets.

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, no redundant information. The first states the action, the second adds an essential behavioral note. Every word 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?

The description is sufficient for a simple tool but not for one with 4 undocumented parameters and no annotations. It fails to explain optional parameters, database usage, or any prerequisites. The behavioral note is valuable but does not compensate for missing parameter guidance.

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 0%, yet the description adds no explanatory detail for any of the four parameters (sql, params, database, dataset_name). It only hints that sql is a SELECT query, but params and database are entirely unexplained. This is a major gap for tool invocation.

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 a specific action: 'Stream a SELECT to Parquet and register it as a Sandbox Dataset.' This distinguishes it from sibling tools like query/execute (which run queries) and list_databases/describe_table (which inspect metadata).

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 implies the tool's use case: exporting query results to a persistent dataset. It clearly differentiates from siblings by its purpose, but does not explicitly state when not to use it or list alternatives.

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