transform_get_fields

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the operation is read-only ('readable', 'probed read-only'), explains ownership semantics for grouping nodes, and notes special behavior like the always-readable 'Function' field and algorithm-filtered option fields. It does not cover error handling beyond the named ICCAP error, but for an introspection tool the key behavioral traits are well disclosed.

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 with relevant ownership mappings and usage guidance, and it front-loads the core purpose before entering exceptions. The ownership enumeration is lengthy but each clause conveys distinct information about different Function types. It earns its length; a small formatting improvement (e.g., bullet list) could make the mapping easier to scan, but no sentence is wasted.

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?

There is no output schema, so the description must communicate what the caller will learn. It does this well by listing the field categories per Function type and clarifying that row counts are probed read-only. It does not explicitly state the return format (e.g., array of string field names), but the phrase 'List the table fields' plus the ownership map makes the return value predictable. For a tool of this complexity, the coverage is strong.

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 documents both parameters at 100% coverage, including the enum for object_type and a note that it is accepted for symmetry. The description adds context about the transform_path being the target of listing, but it does not materially deepen parameter-level semantics beyond the schema. A baseline of 3 is appropriate when the schema is already informative.

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 a precise verb and object: 'List the table fields readable on a Transform for its current Function type.' It goes beyond a generic definition by enumerating ownership rules per function type, which clearly separates this introspection tool from tablevar_get/tablevar_set and other Transform-related siblings like transform_get_data or transform_get_df.

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 final sentence explicitly instructs when to use this tool: 'Use before tablevar_get/tablevar_set to introspect instead of triggering ICCAP_FIELD_NOT_APPLICABLE.' This is concrete, actionable guidance that names the operations it should precede and warns about the error it prevents, leaving no ambiguity about the intended calling context.

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