rememberRead a single Lady Whiskerdown memory by id (as returned by recall). No graph or entity enrichment: the receiver endpoint returns the memory itself, scoped to this key.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Memory id (number or m#N as shown by recall) | |
| kit_session_id | No | Your own session ID from wake; reuse for this conversation. A child or subagent must wake separately, without its parent's ID. |
Changes observed during successful MCP inspections.
Input schema / properties / kit_session_idAdded value: +{
+ "description": "Your own session ID from wake; reuse for this conversation. A child or subagent must wake separately, without its parent's ID.",
+ "maxLength": 160,
+ "minLength": 8,
+ "pattern": "^[A-Za-z0-9:_-]+$",
+ "type": "string"
+}Input schema / properties / id / descriptionPrevious value: -"Memory id"New value: +"Memory id (number or m#N as shown by recall)"Input schema / properties / id / typePrevious value: -"number"New value: +[
+ "number",
+ "string"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide only a title, so the description carries the behavioral burden. It discloses that this is a read-only retrieval, that the response is the raw memory rather than an enriched graph result, and that the result is key-scoped—valuable beyond the schema. It could add auth or error behavior, but for a simple fetch these are minor gaps.
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 convey purpose and behavioral caveat with little waste. The first sentence is front-loaded with the verb and resource; the second adds the disambiguating 'no enrichment' detail. Slight jargon like 'receiver endpoint' and 'scoped to this key' keeps it from being a flawless 5.
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 low-complexity single-id getter with one required parameter and no output schema, the description gives enough context: what it returns, how it is scoped, and how to obtain a valid id. It does not describe return shape or error cases, but those are not substantial omissions for this tool.
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 coverage is 100%, and both parameters already have detailed descriptions, including the m#N id format and kit_session_id constraints. The description reinforces id-based lookup but adds no parameter details beyond the schema, so baseline 3 is appropriate.
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?
Description opens with a specific verb and object: 'Read a single Lady Whiskerdown memory by id,' and immediately disambiguates from recall by noting ids come from recall and that no graph/entity enrichment occurs. This clearly identifies the operation and differentiates it from sibling tools.
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 phrase 'as returned by recall' gives a clear precondition and implies that recall is the tool for producing candidate ids, making the choice between remember and recall reasonably explicit. It stops short of stating a when-not-to-use rule or naming alternatives directly, but the context is sufficient for a simple getter.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.