stream_errors

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It indicates 'recent' and names the log sources, but it does not disclose whether this streams indefinitely, returns a snapshot, how errors are formatted, what happens without parameters, or any polling/retry characteristics. The wait_for_log hint implies polling is possible but does not explain the actual runtime 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 sentences with zero filler. The core purpose is front-loaded, and the alternative-tool guidance is delivered immediately after in a compact second sentence.

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 with two optional parameters and no output schema, so the description is mostly adequate for basic invocation. However, it lacks return-format details and does not clarify tailLength semantics, which are important for an agent deciding how to call the tool correctly. The wait_for_log guidance adds useful context but does not fully compensate for the missing parameter and output behavior.

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 only 50%: deviceId is described, but tailLength is an undocumented bare number. The description does not mention either parameter, so it adds no meaning beyond the schema. 'Recent' hints at tailing behavior but does not explain tailLength's meaning, default, or units.

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 states a specific action ('Get'), a concrete resource ('recent error logs'), and the exact sources ('Metro, Android, and iOS'). It distinguishes this tool from sibling log tools like get_network_logs and get_bundler_logs by scope, and from wait_for_log by explicitly addressing the wait use case.

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 clearly says when to use this tool (when you need recent error logs) and explicitly redirects to wait_for_log(pattern: 'error|exception') for waiting on a specific error, discouraging polling. This is direct, actionable guidance with a named alternative.

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