refine_config

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

Annotations indicate non-readonly, non-destructive, open-world. Description adds auto-preview behavior and the effect of defer_preview. Does not detail persistence or rollback, but adds useful behavioral 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?

Two terse paragraphs: purpose with examples, then defer_preview guidance. No excess words. Highly efficient.

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?

Assumes existence of conversation/session (required params) but does not explain lifecycle context (e.g., must have started refinement via start_table_validation). Output schema exists so return values not needed, but prerequisites are implicit.

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 100% with clear descriptions. Description adds example instructions and clarifies defer_preview usage beyond schema (e.g., 'prevents premature auto-preview'). Baseline 3 improved to 4.

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 states the verb 'refine' and resource 'validation config', with natural language instructions. Examples provided distinguish from sibling tools like 'start_table_validation' or 'approve_validation'.

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 specific guidance on when to set defer_preview to avoid premature auto-preview. However, does not explicitly compare to sibling tools for granular edits (e.g., exclude_row, add_pending_row) that might be alternatives.

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