memory_unlinkDelete a relation between memories without removing the memories themselves. Clean up outdated or incorrect connections in your local memory vault.
Remove one relation from the memory graph (memories stay untouched).
| Name | Required | Description | Default |
|---|---|---|---|
| relation_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal destructiveHint=true, and the description adds valuable behavioral scope by stating exactly what is destroyed—one relation—and what is preserved—memories. This meaningfully clarifies the safety profile of a mutating tool, though it does not cover idempotency or error behavior.
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?
One short sentence front-loads the verb and object, then appends a parenthetical that prevents the most likely misinterpretation. There is no filler, repetition of annotations, or unnecessary schema restatement.
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 and an output schema present, the core call contract is covered: what is removed, what is untouched, and what identifier is needed. The main missing piece is explicit routing to sibling tools, but the operation is simple enough that an agent can infer the usage from the name and context.
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%, so the description carries the burden for explaining relation_id. It only reuses the word 'relation' and does not describe identifier format, validity requirements, or behavior for an unknown id. The single required parameter is self-evident from the schema title 'Relation Id', but the description adds little parameter-level meaning.
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 states a specific verb and resource: 'Remove one relation from the memory graph'. The parenthetical '(memories stay untouched)' clearly distinguishes this from memory deletion tools like memory_forget, so an agent can tell the operation apart without opening schemas.
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?
The description gives no guidance about when to choose this tool instead of alternatives such as memory_link, memory_relations, or memory_forget. It does not state prerequisites, exclusions, or the condition under which unlink is the right operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.