Start a new session to group memories under a shared context. Returns a session_id and accepts optional metadata such as task type or trigger source.
Open a new session, returning a session_id that groups stored memories under a shared context. Attach metadata such as task type or trigger source for later retrieval.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | ||
| metadata | No | Optional session metadata |
Changes observed during successful MCP inspections.
v0.10.12v0.10.11v0.10.8Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies state creation (opening a session) and organizes memories, which is a side effect, but it does not detail permissions, authentication, or potential side effects on existing data. Since no annotations are provided, the description carries the full burden but only partially discloses behavior.
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 concise, consisting of two sentences that directly convey the core purpose and the metadata usage. There is no redundant or irrelevant information.
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 main behavior, return value, and the role of metadata, but it omits an explanation of agent_id and lacks details on error handling or session lifecycle. Given the tool's simplicity and lack of an output schema, the description is reasonably complete but has notable gaps.
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?
The schema covers two parameters, with metadata having a description in the schema and the prose. However, agent_id is required but has no description in the schema or the description text, leaving its purpose unexplained. With schema coverage at 50%, the description does not compensate for the missing agent_id semantics.
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 clearly states the tool's function: it opens a new session, returns a session_id, and groups stored memories under a shared context. It uses a specific verb ('open') and resource ('session'), distinguishing it from the other sibling tools like search or store.
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 context about attaching metadata for later retrieval, but does not explicitly state when to use this tool versus alternatives. It does not mention any specific conditions or exceptions, so usage guidance is implicit rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.