Close an active session by writing a summary of what it achieved, enabling later readers to understand the outcome without opening the full transcript.
Close a session with a summary of what it achieved. The summary is what a later reader sees before deciding whether to open the whole transcript, so write it for someone who was not there.
| Name | Required | Description | Default |
|---|---|---|---|
| session | Yes | Session id. | |
| summary | No | What this session achieved. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral disclosure burden. It mentions the action (close session) and the purpose of the summary, but does not disclose side effects (e.g., termination of session, irreversible closure), permissions required, or the return value. This is insufficient for a potentially destructive operation.
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, no fluff. The primary action is front-loaded, and the rationale for the summary immediately follows. 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?
Given the tool's moderate complexity (two parameters, no output schema), the description is fairly complete: it explains the purpose and gives guidance on summary writing. However, behavior like session closure effect and any implicit requirements (e.g., session must exist) are missing, but the description is sufficient for most use 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?
Schema description coverage is 100%, so the schema documents both parameters. The description adds contextual guidance for the 'summary' parameter (write for a later reader), which is valuable. However, it does not clarify the 'session' parameter's format or any constraints, so it doesn't go beyond schema in that aspect. 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?
The description clearly states the action: 'Close a session' with a summary of achievements. It distinguishes the tool by focusing on session closure and the purpose of the summary, which helps differentiate it from ddflow_session_start and ddflow_session_note.
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 explains that the summary is for a later reader deciding whether to open the transcript, implying when to use this tool (at the end of a session) and how to write the summary. However, it does not explicitly contrast with sibling tools like ddflow_session_note or ddflow_abandon, which might also be considered for ending or noting sessions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.