End the active sub-episode and return to its parent context. Use the session handle to close only your current branch, keeping the session root open.
Close the current open sub-episode and pop back to its parent.
| Name | Required | Description | Default |
|---|---|---|---|
| episode | No | Your session handle — pops only within your own session's subtree; the session root is never closed. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.15.0Input schema / properties / episodeAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Your session handle — pops only within your own session's subtree; the session root is never closed.",
+ "title": "Episode"
+}v0.11.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the state transition ('closes', 'pops') and the scope limitation ('only within your own session's subtree; the session root is never closed'). It does not specify behavior when no sub-episode is open, but the core mutating behavior is clearly disclosed.
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 one front-loaded sentence that states the action, target, and result with no filler. The important constraint is placed in the parameter schema, which is the right location for it. 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 tool with a well-documented schema and an output schema, the description covers the normal invocation scenario and the key limitation. It does not spell out edge cases like calling with no open sub-episode, but the root-never-closed note partially covers boundary behavior. Overall, it is complete enough for an agent to select and use the tool correctly in typical cases.
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 input schema has 100% description coverage and explains the single optional parameter well, including that 'episode' acts as a session handle and that the root is never closed. The tool description itself does not add parameter-level meaning beyond the schema, but it does not need to because the schema already handles it. Baseline 3 is appropriate here.
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 names a specific action ('Close'), a specific resource ('current open sub-episode'), and the outcome ('pop back to its parent'). This clearly differentiates it from sibling tools like memory_episode_start and memory_episode_summary. There is no ambiguity about what the tool does.
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 states a clear condition for use: a sub-episode is currently open and should be closed while returning to its parent. The parameter description adds a useful exclusion by noting that the session root is never closed and that only the caller's own session subtree is affected. It does not explicitly name alternative tools, but the start/end relationship is obvious from the sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.