Folder Diff

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

Annotations (readOnlyHint=true, destructiveHint=false, idempotentHint=true) already indicate safe read behavior. The description goes beyond by detailing what changes are detected and where snapshots are saved (%TEMP%/.fc_snapshots/), but could add more about snapshot persistence or cleanup.

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?

Description is two sentences plus bullet points, front-loaded with purpose, and provides essential info with 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?

Given lack of output schema and complex detection logic, the description explains what it detects and where snapshots are stored. However, it doesn't detail return format or behavior when no snapshot exists.

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% but descriptions are minimal ('Save snapshot', 'Filter extensions'). The description adds context: 'Filter file extensions' and explains extensions usage indirectly, but could be clearer about format (e.g., comma-separated). Higher than baseline 3 due to added detail.

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 it 'Compares the current state of a directory with a saved snapshot' and lists detected changes (new, modified, deleted files). This verb+resource is specific and distinct from sibling tools like fc_list_directory or fc_checksum.

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 provides context on when to use (comparing directory state) and hints at saving snapshots, but does not explicitly tell when not to use or compare with alternatives like fc_detect_duplicates or fc_file_info.

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