run_on_real

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

With no annotations, the description carries the full burden and handles it well: output is size-capped, PII masking is best-effort and explicitly not a guarantee, network is disabled, a timeout applies, and execution is local. It also warns that raw records/identifiers should never be printed, adding important safety context.

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 dense but well organized: concept label, action, safety constraints, and usage guidance. Bolded callouts ('Return AGGREGATES...', 'best-effort') make key instructions easy to parse, and no sentence is filler.

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?

For a code-execution tool with no output schema and no annotations, the description covers the essential operational surface: local execution, data binding, output size, masking caveat, aggregate printing, network isolation, and timeout. It is sufficient for an agent to invoke the tool safely and interpret the result.

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 must compensate. It adds strong semantics for code (Python executed locally) and data_path (bound to DATA_PATH), but timeout is only indirectly covered by 'a timeout applies' and the schema's default, not explained as a configurable parameter.

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 opens with 'COMPUTE-TO-DATA' and clearly states the tool executes Python code locally against a real file at data_path, binding it to DATA_PATH. This is a specific verb+resource pairing and is distinct from siblings like make_synthetic_twin, which implies synthetic data operations.

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 strongly implies when to use it: when you need to compute over real data without pulling raw data into context ('data never enters your context'). It gives actionable guidance to print aggregates and avoid raw records, but it does not explicitly name alternative tools or state when-not-to-use conditions.

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