Retrieve a bounded slice of accumulated terminal session output by offset to inspect specific command results without loading the full log.
Read a bounded slice of accumulated session output by offset.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No | ||
| session_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| offset | Yes | ||
| output | Yes | ||
| truncated | No | ||
| session_id | Yes | ||
| next_offset | No | ||
| oldest_offset | No |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. 'Bounded slice' hints at pagination, but it does not say whether reads are non-destructive, whether offset is a cursor over accumulated output that persists, whether the call blocks until new output arrives, or how much output a default limit returns.
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?
A single tight sentence with the action and scoping mechanism front-loaded. Nothing is padded, though there is too little content rather than too much.
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?
An output schema exists, so return shape need not be described. However, for a paged read tool with zero annotation coverage and three undocumented parameters, the description omits the semantics an agent needs: pagination/cursor behavior, default limit, and offset units.
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. It covers offset implicitly and 'bounded' gestures at limit, but session_id — the only required parameter — is never explained, nor are offset units (characters vs bytes vs lines) or the default/absence behavior of limit.
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?
States a specific verb (Read) and resource (accumulated session output) with the scoping mechanism (bounded slice by offset). It is clear on its own, but it does not distinguish itself from the sibling terminal_read, which an agent could plausibly confuse with this tool.
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?
No when-to-use guidance, no prerequisites, and no mention of alternatives such as terminal_read or session_status. The agent must infer from the name alone whether this is the right read tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.