preview_addressed_edits

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

With no annotations, the description carries the full burden. It clearly states the tool does not write output or mutate the open window, and returns a session for later application. It also specifies that edits are structural and addresses are used. However, it could explicitly state 'read-only' or 'non-destructive' but the implication is strong.

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 somewhat verbose but well-structured. It front-loads the main purpose and then provides necessary usage details. Every sentence adds value, though some of the instruction could be condensed. Overall, it is appropriate for the complexity.

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 has 2 parameters, no annotations, and an output schema, the description covers the workflow, return value (session), and distinction from sibling tools. It provides examples and constraints. However, it lacks explicit error handling details and does not describe the output schema, but the context is sufficient for typical use.

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 schema has 0% coverage for top-level parameters (path and edits have no descriptions), so the description must compensate. It adds meaning by explaining that edits do not require {} named fields, that targets come from inspect_editable_regions, and that operation defaults. This adds significant value beyond the schema.

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 resolves structural addressed edits in file mode without writing output, distinguishing it from live editing and other preview tools. It specifies the exact resource (addressed edits) and action (preview), and the context of use is well-defined.

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 provides explicit usage guidance: when to use file mode over live field writes, to gather all values first, to preview before applying, and what not to do (one call per cell, global replace). It also references the companion tool apply_addressed_edits for the actual write, making the workflow clear.

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