memory_deletePermanently removes a stored memory entry that was recorded in error, such as secrets, noise, or mistakes. Use it to correct bad records; for facts that only became stale, use memory_supersede instead.
Permanently remove a memory. Only for entries that were wrong to record at all (secrets, noise, mistakes). For facts that merely became stale, use memory_supersede.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
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 readOnlyHint=false, so the safety profile is structured. The description still adds real value by stating the removal is permanent and by constraining the legitimate deletion cases, though it says nothing about whether the record is recoverable or whether a confirmation/lookup step is expected.
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 sentences, zero filler, with the permanence warning and the primary use case front-loaded before the alternative routing. Every clause earns its place.
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 one-parameter destructive tool with annotations carrying the safety profile and no output schema, the description covers purpose, permanence, and the sibling split. Only the identifier semantics and post-delete recoverability are left unaddressed.
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 never mentions the single parameter. The agent must infer from the bare property name 'id' (uuid) that it identifies the memory to delete — obvious in practice, but the description compensates for none of the coverage gap on a destructive call.
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 remove a memory') and immediately scopes it against a named sibling. An agent can distinguish it from memory_supersede or memory_update without opening any 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?
Gives an explicit when-to-use ('entries that were wrong to record at all: secrets, noise, mistakes') and an explicit when-not with the alternative named ('For facts that merely became stale, use memory_supersede'). This is exactly the routing guidance a destructive tool needs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.