Correct stored agent memories using plain-language instructions, like retracting a preference or superseding outdated facts with provenance-safe updates.
Natural-language correction, e.g. 'forget that I prefer tea'.
| Name | Required | Description | Default |
|---|---|---|---|
| namespace | No | default | |
| instruction | 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?
No annotations are supplied, so the description carries the full burden. It never states whether the correction is destructive, irreversible, requires confirmation, or what happens to conflicting existing memories; the 'forget' example only weakly implies removal.
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 single short sentence with the core purpose front-loaded and no filler. It is efficient, though the fragmentary phrasing provides no structure beyond the one example.
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?
An output schema exists so return values need not be described, but for a mutation tool with no annotations the definition is thin: no safety/irreversibility notes, no sibling routing, and an unexplained namespace default. More is needed for correct invocation.
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 must compensate. The example ('forget that I prefer tea') usefully illustrates the expected natural-language form of the required instruction parameter, but the namespace parameter is left completely unexplained in both schema and description.
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 recognizable verb+resource ('correction' of memory) and gives a concrete example, so the agent knows roughly what it does. However, it does not differentiate from the close sibling memory_retract, which plausibly also removes/alters memory, leaving the boundary ambiguous.
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?
There is no statement of when to use this tool versus memory_retract, memory_assert, or memory_search. The example hints at a removal-style correction but no exclusions or selection criteria are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.