calculate_field

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

With no annotations, the description fully discloses that the operation is destructive ('irreversibly overwrites column values'), that PYTHON3 executes code in the worker (potential arbitrary code execution), and that confirm=true is required for safety. This exceeds expectations.

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?

Two sentences front-loading purpose and key guidelines. Zero wasted words; 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 complexity (destructive, code execution risk, multiple expression types), the description covers purpose, safety, and recommended usage. With a detailed input schema and output schema, it is adequately complete, though could mention the PathGuard dependency.

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 input schema already provides detailed descriptions for all parameters. The tool description adds marginal value by emphasizing the confirm requirement and ARCADE preference, but does not provide new 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 explicitly states the verb ('Calculate') and resource ('existing field'), and distinguishes from siblings like 'add_field' and 'calculate_geometry' by specifying 'existing field' and 'controlled attribute updates'.

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 recommends using ARCADE for LLM-facing workflows and warns about PYTHON3 requiring confirm=true. It does not explicitly compare to all siblings but gives clear guidance on expression type selection.

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