data_read_csv

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

With no annotations, the description still implies read-only behavior and states that it returns columns, sample rows, and totals. However, it omits important behavioral context such as how limiting works, whether delimiter parsing is robust, error behavior, or sandbox access constraints.

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 two short sentences, front-loads the main action, and contains no filler. Every clause contributes directly to identifying the tool and its output.

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?

An output schema exists, so return values need less explanation, but the description is still incomplete for a three-parameter tool with 0% schema description coverage. It provides no practical guidance on limit or delimiter semantics, leaving an agent to infer behavior from parameter names alone.

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 coverage is 0%, so the description should explain path, limit, and delimiter. It only hints that 'sample rows' relate to limit and that CSV implies a delimiter, but gives no explicit meaning for any parameter, leaving the schema titles to carry the burden.

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 states a specific verb and resource: 'Read a CSV file from the sandbox.' This clearly distinguishes it from siblings like data_read_json and files_read_file, although it does not explicitly name alternatives. The added return summary reinforces the operation.

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?

There is no guidance on when to use this tool versus data_read_json or files_read_file. The sandbox context implies a constrained environment, but the description gives no conditions, prerequisites, or exclusions.

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