Delete a dataset and its files from the server. This is irreversible, so confirmation is required.
Remove a dataset from the server and delete its files. Irreversible.
This is not "unmount": the data on disk goes too. Take a backup first if there is anything in it you would miss.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Dataset name to remove. | |
| confirm | Yes | Must be true. A guard against deleting by autocomplete. |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does well: it discloses that the operation is irreversible and that on-disk files are removed, not just the server registration, which is precisely the failure mode a caller would otherwise underestimate. It omits operational details like required privilege level (admin/maintenance), behavior when the dataset does not exist, and whether dependent graphs go with it.
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?
Front-loaded with the action and its consequence in the first sentence, then a short disambiguation and a short warning. Every sentence earns its place and there is 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?
For a two-parameter destructive tool with no output schema, the description covers the essentials an agent needs: what is destroyed, that it cannot be undone, and to back up first. Missing only peripheral operational context such as permissions required and error behavior on a nonexistent dataset.
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 100%, so the schema already explains both 'name' and the 'confirm' guard against autocomplete deletion. The description adds no parameter-level detail beyond that, so the baseline of 3 applies.
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 names a specific verb (remove/delete) and resource (dataset) and immediately scopes the operation: the files on disk are destroyed too. The explicit contrast with 'unmount' disambiguates it from a plausible alternative a reader might assume, which is exactly the kind of sibling differentiation that earns a top score.
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?
It gives a clear precondition ('Take a backup first'), which implicitly routes the agent to backup_dataset, and it sets the expectation that this is only for data you are willing to lose. It does not, however, explicitly contrast with other destructive-adjacent siblings such as drop_graph or compact_dataset, so the when-not guidance is partial.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.