Preview logs

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

With no annotations, the description carries the full burden of behavioral disclosure. It states that the tool returns recent stdout/stderr, which conveys a read-only operation. However, it does not disclose potential side effects, error behavior (e.g., if preview is not running), or any limitations like log retention. Since the operation is simple and read-only, the basic behavior is covered, but additional details are missing.

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 a single sentence with no filler. It front-loads the core purpose ('Recent stdout/stderr from a running preview') and immediately states the use case ('use this to debug'). Every word earns its place, making it concise and well-structured.

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 two parameters and no output schema, the description should at least clarify parameter usage and error conditions. It does not explain what 'app' means or how 'lines' behaves, nor does it mention what happens if the preview is not running. The description covers the basic purpose and behavior but leaves significant gaps for correct invocation.

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 schema has 0% description coverage, and the tool description does not explain either parameter (app or lines). It does not clarify what 'app' refers to (e.g., app ID, name) or what 'lines' controls (number of log lines). The parameter names are self-evident to some degree, but the description adds no value beyond the schema, leaving the agent to guess exact semantics.

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 purpose: retrieving recent stdout/stderr from a running preview for debugging. It uses a specific verb ('preview') and resource ('logs'), and the context of sibling tools (start_preview, stop_preview) makes its role distinct.

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 clear usage context: it is for debugging a running preview, implying it should be used when logs are needed. It also implies a prerequisite (the preview must be running). However, it does not explicitly mention when not to use it or name alternatives, but given the sibling list, the guidance is sufficient for an agent to infer correct usage.

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