Retrieve a compact summary of a coding session—last request, last action, cwd, branch, and clipped turns—to quickly understand its state for handoffs.
Compact inert summary of a session: last request, last action, cwd, branch, clipped turns. Does not inject.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| session_id | Yes | Session id, live name, title fragment, `agent:ref`, or `latest` |
Changes observed during successful MCP inspections.
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 and explicitly states 'inert' and 'Does not inject,' making the read-only, side-effect-free behavior clear. It also discloses the summary contents and 'clipped turns,' hinting at truncation. It does not cover errors or permissions, but core behavior is well 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?
Two short, dense sentences with no filler. The first sentence front-loads the tool's purpose and output contents, and 'Does not inject' earns its place by clarifying side-effect behavior.
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 tool with no output schema, the description names key output fields and confirms non-injection. Still, it leaves ambiguity about how the limit parameter controls results, what 'clipped turns' means exactly, and behavior when the session cannot be found. A bit more context would make invocation fully safe and predictable.
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 only 50%: session_id is documented in the schema, but limit has no schema description and is never explained in the description. 'Clipped turns' loosely hints at limiting or truncation, but it does not explicitly map the limit parameter to its effect. The description does not compensate for the undocumented parameter.
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 identifies the tool as a compact, inert summary of a session and enumerates the returned fields: last request, last action, cwd, branch, clipped turns. It lacks an explicit verb like 'get' or 'read', and does not directly distinguish itself from siblings like get_session or read_transcript, though 'does not inject' separates it from action-oriented 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?
Usage is implied by 'compact inert summary'—an agent can infer it is for quick session overviews. However, there is no explicit guidance on when to prefer this over get_session, read_transcript, or list_sessions. 'Does not inject' provides a constraint but not a full when/when-not routing rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.