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

Annotations are all false (readOnlyHint, idempotentHint, destructiveHint), so they provide no behavioral signals. The description adds meaningful disclosure: it creates a Saved Version before modification, claims to be safer, and links to API documentation for path conventions. These go beyond the schema and annotations.

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?

Three concise sentences: action, safety/comparison, and path guidance. No filler. The key information is front-loaded, and the documentation link is placed last without disrupting the core message.

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 mutation tool with no output schema and 5 parameters, the description covers purpose, when to use it, a key side effect (Saved Version), and points to external docs for path details. It doesn't address error handling or replace_all behavior, but those are covered by schema or less critical for invocation. Overall, it's sufficiently complete for an agent to decide and call 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?

Schema coverage is 100%, with each parameter described. The description's reference to 'replacing exact text' reinforces old_text/new_text, but this is redundant with schema. The only value-add is the path documentation link, which is more about API conventions than parameter semantics. Since schema already covers everything, baseline 3 is appropriate.

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 precise verb and object: 'Patch one file by replacing exact text.' It immediately distinguishes itself from sibling tools like write_app_file by calling out 'Safer than full overwrite for targeted edits,' which positions it as the refined alternative. The resource (app file) and operation (patch) are unambiguous.

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?

It states when to use this tool: 'for targeted edits' and contrasts with 'full overwrite,' which clearly implies using write_app_file for wholesale rewrites. It also mentions the Saved Version creation, which may influence choice. It doesn't explicitly name alternatives, but the guidance is clear and actionable.

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