Permanently deletes a stored memory file with no recovery. Use archive_memory instead if you might need to restore it later.
Permanently deletes a memory file. NO RECOVERY — be sure. Use archive_memory if you may need it back.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Disambiguate when same id exists in both scopes. | |
| memory_id | Yes | Memory identifier to DELETE. | |
| project_id | No | Further disambiguation for scope=project. |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full load — and it does disclose the single most important behavioral trait: the operation is permanent with no recovery. It does not cover permission/auth requirements or what happens to references or shared-scope copies, which is why it falls short of 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?
Three short sentences, the destructive warning is front-loaded in caps, and the alternative follows immediately. Every sentence earns its place with 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 destructive three-parameter tool with no annotations and no output schema, the description covers the critical risk (irreversibility) and the safe alternative. It omits scope-related consequences (e.g., deleting a shared-scope memory) and permission requirements, leaving modest gaps.
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%, with memory_id, scope enum, and project_id disambiguation all documented in the schema. The description adds no parameter-level meaning 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?
States a specific verb and resource ('Permanently deletes a memory file') and immediately distinguishes itself from the sibling archive_memory by naming it as the non-destructive alternative. An agent can select this tool versus archive_memory without inspecting either schema.
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?
Explicitly gives the condition that should redirect the agent elsewhere: 'Use archive_memory if you may need it back.' That is a concrete when-to-use-this-instead-of-that rule, which is exactly what the sibling routing requires.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.