Manage LLM suggestions for enriching memory facts. Enqueue, retrieve, or apply validated suggestions to explicitly materialize graph facts without overwriting original fields.
Run/get/enqueue optional validated LLM suggestions. action:apply explicitly materializes suggested graph facts without overwriting original memory fields.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| action | No | run | |
| project | No | ||
| namespace | No |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint=false, destructiveHint=false) indicate it is not read-only but not destructive. The description only discloses behavior for the apply action (materializes without overwriting). It does not explain side effects of run, get, or enqueue, leaving the agent unsure whether these mutate state. With no annotation detail beyond false flags, the description carries the burden and fails to cover the action variants.
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 sentences, no filler, and the most important behavioral detail (apply without overwriting) is placed second. It is appropriately concise, though the first sentence is somewhat dense with four verbs packed together.
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?
The tool has 4 parameters, no output schema, and no parameter descriptions. The description does not explain what each action does, what the id targets, or how 'validated LLM suggestions' are produced or used. It also fails to distinguish from memory_add/memory_update. Given the complexity and lack of structured metadata, the description is insufficient 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 explain parameters. It only adds meaning for the action enum (specifically apply), but does not clarify what id refers to, or the purpose of project/namespace. The main phrase 'run/get/enqueue optional validated LLM suggestions' gives context but not parameter-level semantics. It fails to compensate for the schema 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?
The description states the tool operates on optional validated LLM suggestions, with verbs run/get/enqueue/apply. It clarifies that apply materializes graph facts without overwriting, which distinguishes it from direct memory tools like memory_add or memory_update. However, it doesn't explicitly contrast with siblings or define the overall 'enrich' concept beyond suggestion handling.
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?
No guidance on when to use this tool versus alternatives. It never mentions siblings like memory_update or memory_add, nor does it provide conditions for choosing this over direct memory operations. The only hint is that apply materializes suggestions without overwriting, but there is no explicit when-to-use/when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.