read_console

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

With no annotations, the description carries the behavioral disclosure burden. It reveals a stateful behavior: messages are captured since the last open_page, not live. It also clarifies that page errors are included. Minor gaps remain around whether the buffer is cleared or what happens before any open_page, but the core behavior is disclosed.

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?

Two sentences, no wasted words. The first sentence states scope and resource; the second gives a practical diagnostic hint. Both sentences add value and the tool identity is front-loaded.

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 simple read tool with three optional, fully documented parameters and no output schema, the description provides enough context to call it correctly. It explains the resource, the time window, and a common use case. Return formatting is not described, but the absence of an output schema makes this a minor gap.

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 100%, so the parameters are already fully documented in the schema. The description adds no parameter-level detail, but none is needed because level, limit, and pattern all have clear inline descriptions. Baseline 3 is appropriate.

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 names a specific verb and resource: 'Read console messages and uncaught page errors.' It also specifies the temporal scope ('captured since the last open_page'), which distinguishes it from related tools like read_network_errors and get_page_text. This is immediately actionable.

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 a clear diagnostic context: 'JS errors are the usual cause of a page that renders wrong' implies this tool should be consulted when a page renders incorrectly. It does not explicitly name alternatives or exclusions, but the context is strong enough to guide selection.

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