forgetPermanently deletes a specific memory that is incorrect or must not be kept; use to remove bad facts when superseding with a newer entry is not appropriate.
Permanently delete a memory that is wrong or must not be kept. If the fact was replaced by a newer one, prefer remembering the new fact and linking it with relation supersedes.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Memory id, e.g. mem_4kz81q. |
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, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds the permanence framing and, more valuably, the supersession workflow that tells the agent deletion is not the right move for replaced facts. It stops short of describing irreversibility mechanics or failure modes, so not 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 sentences, no waste. The destructive action and its scoping condition lead, and the alternative path follows immediately.
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 single-param, no-output-schema tool whose annotations already carry destructiveness and idempotency, the description covers everything an agent needs: what it does, when it is appropriate, and what to do instead when it is not.
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?
One parameter with 100% schema coverage, so the schema already documents 'id' with its mem_ prefix format. The description adds no further semantic detail about the identifier, which is the baseline expectation when the schema does the work.
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 ('permanently delete') and resource ('a memory') and narrows scope to memories that are 'wrong or must not be kept.' An agent can distinguish this from siblings like remember, reinforce, and link 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 trigger ('wrong or must not be kept') and an explicit when-not with the preferred alternative: if a fact was superseded, remember the new fact and use link with relation 'supersedes' instead. This routes the agent to the correct sibling rather than destroying history.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.