hwp_refresh_fields

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

No annotations are provided, so the description carries full burden. It discloses the core behavior (adding dirty='1' mark), lists affected field types, and notes it's a composite tool. Missing details on potential side effects or required permissions, but the main behavioral traits are covered.

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 two sentences, front-loaded with the main purpose, and includes key details (field types, version, file limitation). Every sentence adds value without redundancy.

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 tool with no output schema and no annotations, the description covers the core functionality, supported field types, and file constraint. It omits explicit mention of overwrite behavior when output_path is omitted (though schema covers it), but overall provides sufficient context for a simple mutation tool.

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 descriptions for all three parameters. The description adds context by listing field types in prose, but does not significantly elaborate beyond the schema. Baseline 3 is appropriate as the schema already documents the parameters adequately.

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 clearly states the tool adds dirty='1' mark to auto-calculation fields in HWPX files to force recalculation. It lists the specific field types (PageNum, TotalPage, etc.) and explicitly mentions '.hwp는 미지원' (no support for .hwp). This distinguishes it from siblings like hwp_get_fields or hwp_fill_fields.

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 indicates when to use: to force recalculation of auto fields on next open, and that it only works for .hwpx files. However, it does not explicitly contrast with sibling tools or provide 'when not to use' guidance beyond the file type restriction.

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