browser_diagnose

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

No annotations are provided, so the description carries the full burden. It mentions what the tool returns but not whether it is read-only, whether it executes scripts, or any potential side effects like modifying page state or requiring network requests. The absence of safety and side-effect disclosure is a significant gap for a diagnostic tool that could be heavy.

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, front-loaded with the core purpose and immediately informative. The first sentence gives a crisp summary, the second adds a helpful analogy. No waste or redundancy, making it exceptionally concise.

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 complex with multiple return types and no output schema. The description enumerates key return categories (performance metrics, console errors, broken images, meta tags, health score), which is a solid summary. However, it lacks details on how the health score is defined or any prerequisites (e.g., requiring a loaded page), leaving some gaps given the richness of the tool.

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 has zero parameters and 100% schema description coverage (empty). With no parameters to explain, the description adds no parameter-specific value, but the baseline 4 applies because there is nothing missing in that regard.

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 does a 'Full page health diagnostic' and lists specific outputs (performance metrics, console errors, broken images, meta tags, health score). This distinguishes it from sibling tools like browser_text or browser_html, which are focused on content retrieval rather than health assessment.

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 the analogy 'Like Lighthouse for your agent' which suggests a comprehensive audit use case, but it does not explicitly state when to use this tool versus alternatives (e.g., using browser_title for a quick check). There are no exclusions or direct comparisons to siblings, leaving usage guidance implied rather than explicit.

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