delete_rows

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

With no annotations, the description carries the full behavioral disclosure burden and does so thoroughly. It labels the operation as destructive, explains the preview vs. actual deletion behavior, documents the confirm default, and specifies both return shapes. This is far beyond what the bare input schema conveys.

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 compact yet information-dense: purpose, safety workflow, args, return values, and example are clearly labeled and easy to parse. The destructive warning is front-loaded, and every sentence contributes to safe and correct invocation.

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 covers all needed context: how to preview, how to confirm, what arguments to pass, what responses to expect, and a concrete example. Despite having no annotations, an agent has everything necessary to invoke the tool safely and interpret its output.

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%, so the description fully compensates by providing a dataset example, row_ids example with mutual exclusivity, a structured conditions example, and confirm default semantics. Each parameter is given practical meaning beyond its raw type definition.

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 starts with a specific verb and resource: 'Delete rows by explicit ids, or in bulk for every row matching a filter.' This clearly distinguishes it from siblings like delete_dataset, add_rows, and update_rows, and identifies the two supported deletion modes.

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 gives explicit workflow guidance: call with confirm=false first, tell the user what will be lost, then re-invoke with confirm=true after agreement. It also clarifies that row_ids and conditions are mutually exclusive. It doesn't explicitly name alternative sibling tools for when not to use it, but the usage context is otherwise strong.

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