list_fields

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

No annotations are provided, so the description must carry the behavioral burden. It only implies a read operation by saying 'Return', but discloses nothing about behavior for invalid or nonexistent datasets, supported dataset sources, or whether it errors or returns an empty list.

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?

A single, front-loaded sentence contains only necessary information: action, output, and target resource. No filler or redundancy exists.

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 operation is simple and the output schema covers return structure, so the description is nearly sufficient for invocation. However, missing usage guidance and behavioral context such as error handling or supported dataset types prevent it from being fully complete for an agent evaluating it in isolation.

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% and the schema only names 'dataset'. The description adds that the dataset is a feature class or table, which provides some meaning, but it does not specify accepted path formats, dataset identifiers, or workspace context, leaving part of the parameter semantics to inference.

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?

Uses specific verb 'Return' and explicit resource 'field metadata for a feature class or table', clearly distinguishing it from sibling tools like list_mxd_layers or describe_dataset. The object type and output are both named, so an agent can identify the operation at a glance.

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?

No guidance is given about when to choose this tool instead of alternatives such as describe_dataset or search_arcpy_tools. The description only states what it does, leaving the agent to infer intended usage without explicit context or exclusions.

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