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

Goes well beyond the annotations: it discloses the cycle and root restrictions, that no overwrite occurs, that destination sharing may alter access (explaining the destructiveHint), and the required scopes. The retry guidance also warns that an uncertain result must be verified rather than blindly repeated.

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?

Five short declarative sentences, front-loaded with the core action and followed by constraints, permissions, and recovery advice in priority order. 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?

A mutation tool with an output schema, so return values need no explanation; the description instead covers the constraints, side effects, permission requirements, and failure handling an agent needs to call it safely.

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 0%, so the description must carry the load; "move a folder between folders" implies a source and a destination but never maps these to folder_hash vs target_folder_hash or states which is which. The pattern-based format is only in the schema.

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?

States a specific verb and resource ("Move a folder") plus a scope constraint ("between folders of the same owner"). The folder-vs-file distinction implicitly separates it from filesfm_move_file, but no sibling is named explicitly.

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?

Gives concrete when-not conditions (roots, self, descendants, overwrite) and a prerequisite (files:write and account permissions), plus recovery advice before retrying. It stops short of naming alternatives such as filesfm_rename_folder or filesfm_move_file for adjacent tasks.

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