Read new output from a background process since the last read, or fetch all buffered output with all: true. Use it to monitor long-running shell jobs without missing earlier results.
Read new output from a background process since the last read (or all buffered output with all: true).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| all | No |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds useful context beyond those annotations by disclosing the stateful cursor behavior ('since the last read') and the buffering scope ('all buffered output with all: true'). It does not mention whether the call blocks when no new output is available, but the added cursor semantics are a meaningful contribution.
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 sentence that front-loads the core action and then qualifies it with the parameter override. No wasted words; every clause 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?
The tool is simple (2 parameters, no output schema), and the description tells the agent what is returned and how to change the read scope. It omits whether the call blocks when no new output exists and does not describe the output format, which is a minor gap given no output schema is present and annotations cover safety.
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 carry the full burden. It explains the optional 'all' boolean's effect (return all buffered output) and implies that 'id' is the background process identifier, but it does not specify the format or type of the id beyond context. Partial compensation for the low schema coverage.
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 clear verb (Read) and resource (new output from a background process) with a scoping qualifier (since the last read or all buffered output). It implicitly distinguishes itself from pty/job siblings by specifying 'background process', but it does not name an alternative sibling tool by name.
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 implies usage by explaining the 'since the last read' default and the 'all: true' override, which guides the agent on how to call it. However, it never states when to prefer this tool over siblings like job_output or pty_read, leaving alternatives to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.