filesystem_manage

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

With no annotations, the description carries the full burden. It discloses important behaviors: write_text triggers a filesystem scan and includes a cleanup field; scan explains it rebuilds global class_name table and is single-flighted. However, it omits details like error handling, permission requirements, or behavior for edge cases.

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 lengthy with multiple paragraphs and bullet points. It is front-loaded with the purpose, but some sections (e.g., the scan explanation) are verbose. The structure clearly separates operations, but could be more concise.

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 tool's complexity with multiple operations and an existing output schema, the description covers each operation's purpose and some return details (e.g., scan returns scan_completed and global_classes_registered_delta). It lacks information about error conditions or the exact structure of results, but is largely adequate.

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 compensate. It explains the 'op' enum and provides per-operation parameter details (e.g., read_text requires path, write_text requires path and content, reimport expects a list of paths). However, the 'params' parameter itself is not fully described in JSON structure, relying on the operation context.

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 is for 'Project filesystem access via the Godot editor's EditorFileSystem' and enumerates specific operations (read_text, write_text, reimport, scan, search) with distinct purposes. This distinguishes it from sibling tools like script_create or resource_manage.

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 does not explicitly state when to use this tool versus alternatives. While the scan operation provides some context (e.g., after adding class_name scripts), there is no general guidance on when to choose filesystem_manage over similar tools like script_manage or resource_manage.

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