sanitize_csv_securely

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

No annotations are present, so the description carries the full burden. It discloses specific cleaning behaviors ('strips leading/trailing whitespace, standardizes delimiters to commas, and resolves malformed rows') and sandbox-related constraints ('secure remote Azure sandbox environment', 'sandbox memory limits and payload timeouts'). This gives good insight into side effects and limitations, though it doesn't detail the output format (covered by output schema).

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 efficiently structured: a clear opening sentence, a one-sentence purpose, and a bulleted list of usage guidelines. No redundant information; every sentence adds value.

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 the tool's simplicity (one parameter), a complete schema, and an output schema, the description covers all necessary aspects: purpose, when to use, constraints, and behavioral specifics. It is a well-rounded description for this tool's complexity.

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% for csv_content, so baseline is 3. The description adds meaning by specifying that csv_content 'must be a plain-text string representation of a CSV' and reiterates the text-only requirement, which supplements the schema description 'raw, unformatted CSV text string that requires cleaning.'

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?

Description clearly identifies the tool's function: 'Sanitize raw CSV data by cleaning and normalizing it within a secure remote Azure sandbox environment.' This uses a specific verb+resource (sanitize CSV) and the 'Use this tool to prepare messy tabular data' phrase further clarifies intent. It is distinct from sibling tools like execute_code_securely or generate_plot_securely.

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 usage context: 'Use this tool to prepare messy tabular data for downstream processing' and includes concrete when-not constraints like 'Do not pass binary files or Excel (.xlsx) formats; strictly text-based CSV data.' However, it does not name alternative tools for cases where a different tool would be appropriate, so it falls short of a 5.

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