transaction_apply

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

With no annotations, the description fully carries the burden and does so excellently: atomicity, pre-validation against on-disk content, rollback of already-written files on partial failure, crash-durable fsync, per-path locking, and response format with diffs are all disclosed.

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?

Every sentence earns its place. The description front-loads the core purpose, then packs behavioral guarantees, usage guidance, limits, and response format into a dense, well-structured block with no filler.

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 complexity of a multi-file transactional write tool and no output schema, the description is remarkably complete: it covers validation, failure modes, durability, concurrency, operation limits, and response contents. An agent can predict exact behavior before invoking.

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 coverage is 100%, so baseline is 3. The description adds meaningful operational context beyond the schema: it explains that all operations are validated first and no writes occur if any old_string is missing or ambiguous, and clarifies the rollback behavior. This goes beyond simply restating parameter names.

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?

Opens with a specific verb+resource+scope: 'Apply str_replace edits across multiple files atomically.' Clearly distinguishes from single-file edit tools like edit_file and whole-file write_file, and mentions concrete use cases like cross-file rename.

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?

Explicitly states when to use: 'Use for refactors that must land as one unit (cross-file rename of a string, coordinated config + caller updates, etc.)'. It implies single-file edits are better served by simpler tools but does not explicitly name them as alternatives; the sibling list and schema reference to edit_file provide context.

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