session_readList your agent's past sessions or read a selected session's text and tool names. Use handles or native IDs to retrieve redacted conversation history.
Without handle/native_id: list your own agent's past sessions. With one: read it (text and tool names, redacted).
| Name | Required | Description | Default |
|---|---|---|---|
| here | No | ||
| tail | No | ||
| limit | No | ||
| handle | No | ||
| offset | No | ||
| max_chars | No | ||
| native_id | No |
Changes observed during successful MCP inspections.
v0.16.20Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already establish this as a safe, read-only, non-destructive operation, and the description adds useful disclosure that returned session content is redacted and includes text and tool names. However, it says nothing about pagination, defaults, limits, or how the optional parameters affect 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?
Two short sentences with the main behavioral distinction front-loaded and no wasted verbiage. The terse style is appropriate, even though it contributes to the semantic gaps captured elsewhere.
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 tool with seven optional parameters, no output schema, and no schema descriptions, the description is too thin. It explains the central list/read distinction but omits how pagination, tail, limits, and location scoping (here) alter results.
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 0%, so the description must compensate, but it only explains handle/native_id and their absence/presence effect. It leaves here, tail, limit, offset, and max_chars completely undocumented, which is a significant gap for seven parameters.
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 two modes: listing the agent's own past sessions when no identifier is supplied, and reading a specific session when handle/native_id is supplied. The verb and resource are identifiable, though it does not explicitly differentiate itself from siblings like recall or discover.
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?
It gives explicit conditional guidance: omit handle/native_id to list sessions, include one to read a session. It does not mention alternatives among sibling tools, but the mode-selection condition is clear enough for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.