preview_addressed_edits

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

Discloses that the tool does not mutate the open Hangul window, returns a session for later application, and explains behavior of edits (no named fields, structural addresses, no global replace). No annotations exist, so description covers the burden fully.

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 a single dense paragraph with multiple instructions. While it front-loads the main action, it could be more concise and better structured (e.g., bullet points) given the volume of detail.

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?

Covers use cases, behavioral constraints, integration with apply_addressed_edits, and mentions output session. With an output schema present, return values need not be explained. Leaves minor ambiguity about session_id but is largely complete.

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?

Though top-level parameters lack descriptions (0% coverage per context), the description adds semantic value by explaining how to structure edits (no named fields, use structural addresses) and providing target format examples. This supplements the schema's nested descriptions.

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 it resolves structural addressed edits in file mode without writing output, distinguishing it from the sibling tool apply_addressed_edits that writes later. It specifies the purpose as previewing to confirm edits resolve to intended targets.

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 explicit when-to-use guidance: use for whole-template completion, gather values first, start in file mode, preview before applying. Also warns against mixing live field writes and falling back, and names the alternative apply_addressed_edits for writing.

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