query_bill_to_file

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

With no annotations, the description carries the full burden. It discloses streaming behavior (does not accumulate in memory), return format with path/row_count/bytes, partial write on error, truncation at max_rows, and local file output. This is rich behavioral disclosure beyond the schema, though it doesn't mention overwrite 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?

The description is structured with an intro, return format, and Args section. While somewhat long, every sentence adds value—purpose, behavior, return format, and parameter semantics. It is front-loaded with purpose and avoids fluff.

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 7 parameters, no schema descriptions, and no annotations, the description covers all parameters, return format, error handling, and use case. It lacks only minor details like CSV header specifications, but is otherwise 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?

The schema has 0% description coverage, so the description fully compensates by explaining each parameter with examples, allowed values, defaults, and truncation behavior. This adds substantial 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 the tool auto-paginates and streams query results to a local file, explicitly noting it is for large data exports (over 10k rows). This distinguishes it from sibling tools like query_bill which likely return in-memory results.

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 states the tool is suitable for large data volumes (>10k rows) and suggests using the Read tool for spot-checking or pandas/polars for processing. However, it does not explicitly name an alternative query tool for smaller datasets, so it lacks explicit exclusions but provides clear context.

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