Delete all memories in a namespace after previewing with dry run to avoid accidental data loss.
Delete all memories in a namespace. DESTRUCTIVE - use dry_run first.
| Name | Required | Description | Default |
|---|---|---|---|
| confirm | No | Confirm deletion (required when dry_run=false) | |
| dry_run | No | Preview deletion without executing | |
| _agent_id | No | Optional agent identifier for request tracing and per-agent rate limiting. | |
| namespace | Yes | Namespace to delete |
Changes observed during successful MCP inspections.
v1.11.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. 'DESTRUCTIVE' flags the risk and 'use dry_run first' gives a safe workflow. It could add irreversibility or confirmation requirements, but the warning is sufficient for a deletion tool.
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?
A two-clause sentence that leads with the operation and immediately adds the critical warning. No filler or redundant schema repetition.
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 simple destructive operation with a fully documented schema and no output schema, the description plus the schema provide everything an agent needs to invoke it safely. The optional _agent_id and the dry_run/confirm semantics are already covered in the schema.
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 coverage is 100%, so the baseline is 3, but the description adds safety-meaning by instructing dry_run-first behavior beyond the schema's parameter defaults. This helps an agent act correctly without reading deeper into the parameters.
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 clear verb and resource: 'Delete all memories in a namespace.' This is distinct from siblings like forget/forget_batch or rename_namespace. The word 'all' also signals full-namespace scope.
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?
Provides clear context: the operation is destructive and should be preceded by dry_run. It does not explicitly name alternatives or exclusions, but the dry-run-first instruction is actionable and contextually useful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.