patch_section

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

No annotations exist, so the description must disclose behavior fully. It states that the tool does not write, returns a unified diff as a string, and returns empty string if no changes. It lacks details on permissions, idempotency, or side effects, but the core safety (read-only) is clear.

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 two sentences, each adding essential information: what it does and when to use it. No wasted words.

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?

Despite having an output schema, the description lacks parameter explanations and behavioral details (e.g., error conditions, prerequisites). It is complete in stating purpose and return type but fails to cover the three required parameters, leaving significant gaps.

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 input schema has 3 required parameters (file_path, path, new_content) with 0% description coverage. The description provides no explanation of what these parameters mean, leaving the agent to infer from the tool name and sibling tools. This is insufficient.

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 returns a unified diff of what replace_section would do without writing. It uses specific verb 'Return' and resource 'unified diff', and distinguishes itself from replace_section by emphasizing preview vs. write.

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 says 'Useful for previewing changes before committing them,' which provides clear context for when to use. It implicitly contrasts with replace_section but does not explicitly state when not to use or list other alternatives.

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