typst_delete_filesPermanently delete files from a Typst project using project ID and project-relative paths or file IDs, with confirmation before removing files not explicitly requested.
Permanently delete files from a project. Confirm with the user before deleting anything they did not explicitly ask to remove.
| Name | Required | Description | Default |
|---|---|---|---|
| paths | Yes | ||
| project_id | Yes | Project ID from typst_list_projects, e.g. 'pAbC123dEf456gHi789jKl' |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=false, but 'Permanently' adds the non-obvious fact that deletion is irreversible with no trash or undo path. The confirmation instruction is extra behavioral context beyond the annotations. Missing details on partial failure or batch semantics keep it from a 5.
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?
Two tight sentences with the destructive scope front-loaded and the safety instruction second. No filler or redundant restatement of the schema.
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 destructive batch mutation with no output schema needs more than this: it omits what happens on nonexistent paths, whether deletion is atomic across the paths array, and what is returned. Annotations carry the safety profile, which keeps it at minimum-viable rather than inadequate.
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 only 50%, and the description adds nothing about the parameters — it does not clarify that 'paths' accepts both project-relative paths and file IDs, or how multiple paths are handled. The description is silent where the schema is thin.
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 ('Permanently delete files from a project'), which is clearly distinct from typst_delete_project at the noun level. It does not explicitly contrast with the project-level deletion sibling, so the agent must infer the scope difference.
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?
Adds a real precondition ('Confirm with the user before deleting anything they did not explicitly ask to remove'), which is useful guidance for a destructive tool. However, it gives no routing advice among siblings such as typst_delete_project or when to prefer typst_edit_file over deletion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.