read

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of disclosing behavior. It adds important context: it does not send anything, and it only returns output not already returned (same cursor semantics as send). However, it does not explicitly mention that it can auto-answer '--More--' prompts or has timeout/quiet behavior (though these are covered in parameter descriptions). It provides some transparency but could go further in describing the wait/collection 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?

The description is two short sentences, with the primary purpose front-loaded in the first sentence. Every sentence conveys meaningful information without redundancy. It is concise and efficiently structured, allowing an agent to quickly grasp the core function and key behavioral nuance.

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 simplicity (no output schema, no annotations, but 4 well-documented parameters), the description provides adequate context for use: when to use it, its key behavior (cursor semantics), and that it does not send input. It could optionally explain the return value format, but since the tool collects output and the schema covers parameters, this is sufficient. It is almost as complete as the high-calibration example.

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?

The input schema covers 100% of the parameters with descriptions, so the baseline is 3. The tool description itself does not add additional parameter semantics beyond what the schema already provides. It references 'more_limit' which is a concept from a previous tool, but that does not clarify the parameters themselves. Therefore, no extra value is added by the description.

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 tool's function: 'Collect further output without sending anything.' It uses a specific verb ('collect') and resource ('output'), and distinguishes itself from sibling tools like 'send' by explicitly noting it does not send anything. This makes the tool's purpose immediately clear.

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 provides explicit use cases: 'For slow programs, or to continue after a `more_limit`.' This tells the agent when to use this tool. However, it does not explicitly contrast with alternative tools like 'peek' or 'status', though the mention of 'same cursor semantics as send' implies a relationship. The guidance is useful but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.