apply_addressed_edits

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

With no annotations, the description carries full burden. It discloses that the tool does not mutate the open Hangul window, keeps repeated text explicit with structural scope, and that the plan came from structural addresses. This is comprehensive 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?

The description is verbose at ~150 words with multiple long sentences. It could be more concise by trimming redundant explanations about structural scope and repeated text. The first sentence is good, but the rest is dense.

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 and 2 required params, the description adequately covers purpose, context, and behavioral traits. An output schema exists to cover return values. The description addresses when to use and what not to do, making it complete for task selection.

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 description coverage is 0%, so description must add meaning. It explains that session_id comes from preview_addressed_edits and out_path is required. While minimal, it clarifies the role of each parameter, though no format or constraints are provided.

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 'Write the previewed addressed edits to a NEW file-mode output copy,' providing a specific verb and resource. It distinguishes from siblings like apply_to_current_hwp_document by emphasizing file-mode output and no mutation of open windows.

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 gives clear guidance: use after preview_addressed_edits, gather all values first, and avoid mixing with live field writes. It implies this is for file-mode, not for open documents, but does not explicitly list sibling alternatives.

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