Delete a memory entry by ID to remove outdated or incorrect information. Users can delete their own entries; admins can delete any entry.
Delete a memory entry created by the current actor. Admins may delete any memory entry.
| Name | Required | Description | Default |
|---|---|---|---|
| entry_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide no behavioral hints, so the description carries the full burden. It discloses the actor-based permission constraint and implies destructive action via 'Delete', but it does not explicitly state permanence, irreversibility, or side effects. This is adequate but not rich.
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 short sentences, zero filler. The main action and the key authorization nuance are front-loaded, and every word 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 single-parameter delete tool with an output schema, the description covers purpose and permissions adequately. It omits an explicit note about permanence, which is a minor gap given the destructive nature, but the overall context is sufficiently complete.
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 0%, so the description must compensate. It links entry_id to 'memory entry' but does not explain how to obtain the value (e.g., from a search result) or any format details. Minimal compensation exists, but an agent still has to infer the ID's origin.
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 ('Delete'), resource ('memory entry'), and scope ('created by the current actor' with admin override). This clearly differentiates it from memory_write and memory_search without needing to inspect 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 provides clear context on who can delete which entries (own entries vs. admins deleting any), but it does not explicitly name alternatives like gateway_memory_write for creation or gateway_memory_search for finding entry IDs. The condition is clear, yet no exclusions or alternative route is stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.