batch_modify

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

With no annotations, the description carries the full burden and excels. It discloses destructive behavior with a warning and backup mechanism, explains transaction semantics (all_or_nothing rollback vs best_effort), and clarifies that default review returns diffs without writing. It also details return shapes for both review modes, going well beyond minimal requirements.

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 long but every sentence earns its place. It is logically structured: purpose first, then usage examples, transaction behavior, exclusions, safety warning, and return shapes. No fluff or repetition; the density is justified by the tool's 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's complexity (batch editing, transaction modes, review modes) and the absence of an output schema, the description is remarkably complete. It covers use cases, alternatives, safety, transaction semantics, and detailed return shapes. There are no significant gaps for an AI agent to invoke it correctly.

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 description adds meaningful context for `transactionMode` and `review`, explaining rollback behavior and the write-vs-preview distinction. It does not elaborate on `backend`, `parallel`, or `stopOnError` beyond schema defaults, so not every parameter is enriched. Overall, it supplements the schema where it matters most.

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 opens with a specific verb+resource: 'Apply the SAME natural-language instruction independently to each file.' It clearly distinguishes from siblings by explicitly stating it does not find cross-file references and naming `refactor` and `modify_file` as alternatives. Examples make the scope unmistakable.

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 explicit guidance: 'Use for sweeping consistent edits' with concrete examples, then states what the tool does NOT do and names alternatives: 'For symbol renames that must update callers, use `refactor`. For one file with custom instructions, use `modify_file`.' This covers both when-to-use and when-not-to-use.

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