Replace an outdated memory while preserving its revision history. Dependent memories are flagged for review to keep linked knowledge accurate.
Replace a memory while preserving history. Dependents of the old memory will require review.
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | ||
| tags | No | ||
| type | No | ||
| scope | No | ||
| old_id | Yes | ||
| reason | No | ||
| source | No | ||
| metadata | No | ||
| statement | Yes | ||
| confidence | No | ||
| depends_on | No | ||
| expires_at | No | ||
| valid_from | No | ||
| review_after | No |
Changes observed during successful MCP inspections.
v0.2.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose two non-obvious behaviors: history is preserved and dependents of the old memory are flagged for review. However, it omits whether the old memory becomes inactive, how the dependents are surfaced, and any permission or irreversibility notes for a 14-parameter mutation.
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, front-loaded with the action and its key benefit, with zero filler. It is well formed; brevity is only a minor issue here because the underlying gaps are semantic, not stylistic.
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?
A 14-parameter mutation tool with no annotations, no output schema, and no parameter documentation needs far more than two sentences. The description covers the concept but leaves the mechanics of the call largely unspecified.
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 14 parameters, and the description mentions none of them. old_id, statement, reason, confidence, scope, depends_on and the rest of the fields are left entirely unexplained, so the description cannot compensate for the coverage gap.
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 ('Replace') on a specific resource ('a memory') plus the distinguishing behavioral trait of preserving history. That separates it from a plain overwrite, though it never names the sibling it competes with (e.g. invalidate or remember) to make the distinction explicit.
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 when-to-use guidance and doesn't route to alternatives. An agent facing 'update a memory' has to guess whether to use supersede, invalidate, or remember; the only hint is the downstream note that dependents need review, which implies a scenario but not a decision rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.