ask_memoryRetrieve approved conclusions or raw evidence from stored project memory by asking a question. Returns answers with exact sources and a recall ID for feedback.
Ask approved conclusions first, then scoped or explicitly requested raw evidence. Returns an answer, exact provenance, and a recallId for feedback.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | ||
| tags | No | ||
| limit | No | ||
| question | Yes | ||
| namespace | No |
Changes observed during successful MCP inspections.
v0.1.7Input schema / properties / kindAdded value: +{
+ "enum": [
+ "memory",
+ "conclusion"
+ ],
+ "type": "string"
+}Input schema / properties / namespaceAdded value: +{
+ "minLength": 1,
+ "type": "string"
+}Input schema / properties / tagsAdded value: +{
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds useful behavioral context beyond those flags: it reveals the retrieval order and the exact output contract (answer, provenance, recallId). This helps an agent predict side effects and response shape without contradicting the annotations.
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?
The description is two sentences with no filler. The core behavior is front-loaded in the first sentence, and the second sentence efficiently states the return value. Every clause 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?
The description covers the retrieval strategy and the output contract, which is helpful given the lack of an output schema. However, with five parameters and no schema-level descriptions, an agent still lacks details on parameter meanings and edge behavior such as limit handling or namespace scoping. It is adequate but not fully 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 description coverage is 0%, so the description must compensate for undocumented parameters. It partially maps 'approved conclusions' to kind=conclusion and 'raw evidence' to kind=memory, and 'scoped' hints at tags or namespace. However, it does not explain limit, tags, namespace, or the full enum semantics, leaving significant ambiguity for a five-parameter 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?
The description states a specific action ('Ask'), a resource (memory), and a distinctive retrieval order ('approved conclusions first, then scoped or explicitly requested raw evidence'). It also names the return payload, which helps an agent understand what the tool produces. It doesn't explicitly contrast itself with sibling tools like search_memory or recall_memory, but the behavior is clear enough to differentiate.
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 clear usage context: prefer approved conclusions, then fall back to raw evidence when scoped or explicitly requested. It implies when to use this tool for memory queries and what kind of output to expect. It doesn't state when not to use it or name alternatives, so it stops short of full exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.