Preview edits

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds meaning beyond those: it previews against a throwaway copy, includes every session edit already applied, and guarantees a green preview cannot disagree with a subsequent apply. It also discloses that author and mode influence engine refusals, which is a non-obvious behavioral detail.

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 sentences, front-loaded with purpose, and every clause earns its place: the throwaway-copy guarantee, the session-state inclusion, and the author/mode rationale. No redundant filler or schema repetition.

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 read-only preview tool with rich annotations and an output schema, the description covers purpose, state assumptions, non-mutation, and a strong consistency guarantee. An agent has what it needs to select and invoke the tool; remaining details like return values are handled by the output schema.

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 the description must compensate. It adds useful rationale for author and mode (engine refusals depend on both), and 'batch of edits' gestures at edits, but it leaves session_id entirely implicit and does not explain the shape or constraints of the edits parameter, which the schema only partially covers via nested fields. This is meaningful but incomplete compensation.

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 opens with a specific verb and object: 'Report what a batch of edits WOULD do' and immediately clarifies it is non-mutating ('writing nothing'). This clearly differentiates it from sibling apply_edits and commit_document without needing to open the schema.

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 implies the workflow: run a preview before the 'apply that follows it,' and the throwaway-copy engine guarantees agreement. It does not explicitly name apply_edits as the alternative or state when not to use preview, so it falls short of a 5 on explicit routing.

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