Delete a file or folder

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the destructive nature is covered. The description adds 'Permanently delete' (irreversibility) and 'Requires human confirmation' (interaction requirement), which go beyond the annotations. This provides meaningful behavioral context for a high-stakes operation.

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?

A single, front-loaded sentence with no filler. The core action and the critical confirmation requirement are both stated efficiently. The description earns its place without redundancy.

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 the destructive nature and lack of parameter documentation, the description is very brief. It does not explain what constitutes a valid path, whether deletion is recursive for folders, what happens to child files, or what errors might occur. The confirmation requirement is mentioned, but for a tool with 0% schema coverage and no output schema, this is insufficient for an agent to call it safely and 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 description coverage is 0% and the description provides no explanation of 'projectId' or 'path'. While 'projectId' is self-explanatory, 'path' is ambiguous – it could be relative, absolute, file-only, or folder-only. The description gives no format or examples, leaving the agent to guess. For a destructive tool, this is a critical gap.

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 states a specific verb ('permanently delete'), the resource type ('document, file, or folder'), and the context ('from an Overleaf project'). It clearly differentiates from sibling tools like delete_project (whole project) and archive_project (non-destructive archive). The wording is 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?

The description implies usage for file/folder deletion within a project but does not explicitly mention alternatives or when not to use it. The note 'Requires human confirmation' signals a precondition but no guidance is given about when to prefer this over delete_project or archive_project. The sibling list includes delete_project, but the description does not route the agent away from it, leaving some inference required.

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