Fetch research records ordered by recorded event time, excluding reference entries, to view recent observations, claims, and revisions. Use for audit and progress checks.
Return latest non-reference records, ordered by recorded event time.
| Name | Required | Description | Default |
|---|---|---|---|
| top_k | No |
Changes observed during successful MCP inspections.
v0.9.3Output schema / (root)Previous value: -{
- "additionalProperties": true,
- "title": "memory_latestDictOutput",
- "type": "object"
-}New value: +nullv0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds useful behavioral context by scoping to non-reference records and specifying ordering by event time, but it does not explain what makes a record 'non-reference' or how top_k limits the result set.
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?
One sentence with no filler; the main action, record scope, and ordering are all front-loaded. Every word 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?
For a one-parameter read-only tool this is nearly sufficient, but the undefined term 'non-reference records' and the lack of an output schema leave some ambiguity about what the agent will receive. The safe annotations reduce the risk, but a definition of the record scope would make it 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%, and the description never mentions the only parameter, top_k. The parameter name and default imply it is a count, but the description does not compensate for the missing schema descriptions by explaining valid values, behavior, or interaction with the ordering.
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 uses a specific verb ('Return') and identifies a clearly scoped resource ('latest non-reference records') with an explicit ordering criterion ('recorded event time'). It stops short of contrasting with siblings like memory_search_candidates, so it is clear but not fully differentiated.
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 phrasing implies use when the agent needs the most recent non-reference memory records, and the read-only annotations signal safe retrieval. However, it gives no explicit when-to-use or when-not-to-use guidance and does not mention alternative tools such as memory_search_candidates or memory_audit_ledger.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.