memory_updateAmend an existing memory in place to correct details or add information without changing its core topic; use supersede instead when the underlying belief changes.
Amend an existing memory in place. Use for corrections and additions that do not change what the memory is about; use memory_supersede when the belief itself changed.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| body | No | ||
| tags | No | ||
| title | No | ||
| source | No | ||
| importance | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=false, and 'in place' is consistent with that non-destructive profile, so no contradiction. However the description never states the key behavioral question for an update tool: whether omitted fields are preserved (patch) or cleared, and whether the original revision is retained. With annotations covering the safety profile, the bar is lower, but this is a meaningful gap.
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 tight sentences with zero waste; the core purpose is front-loaded and the alternative follows immediately. Nothing could be cut without losing a routing decision.
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?
Purpose and sibling routing are fully covered, but with no output schema and 0% schema description coverage, the definition leaves an agent unable to predict update semantics (partial vs full replacement) or parameter meaning. Adequate for selection, thin 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% across 6 parameters, so the description carries the full burden and provides nothing: no mention of id being the required key, no indication that body/title/tags/source/importance are optional partial updates, no note on importance's 1-5 range or tag replacement semantics. This is a clear miss for a 6-param tool.
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 and resource ('Amend an existing memory in place') and immediately distinguishes itself from the sibling memory_supersede. An agent can tell which of the two mutation tools to reach for without opening either 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?
Explicitly gives the selection rule: corrections/additions that don't change the memory's subject use this tool, while a changed belief routes to memory_supersede. Both the when and the alternative are named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.