cdp

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

With no annotations, the description carries the full behavioral burden, but it only says the command is raw. It does not disclose side effects, permissions, whether arbitrary commands can mutate or destroy state, error behavior, or return format.

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 front-loaded sentence with no wasted words. It is appropriately sized for a simple low-level dispatch tool.

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 an arbitrary CDP escape hatch with no annotations and no output schema, the description is insufficient. It omits expected return values, error handling, page targeting behavior, and any warning about potentially destructive protocol commands.

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 67%: method has an example and pageId has a default note, but params is undocumented. The description adds no meaning beyond the schema and does not compensate for the undocumented params object.

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 verb and resource: send a raw Chrome DevTools Protocol command to a page. This clearly distinguishes it from higher-level siblings like evaluate_script, click, or navigate_page, though it does not explicitly name an alternative.

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?

There is no guidance on when to use this low-level tool versus the many higher-level browser automation tools. It implies an escape hatch through 'raw', but gives no when-to-use, when-not-to-use, or prerequisite context.

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