ai_browser_agent

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

The description states the agent can click links, fill forms, and perform actions, which implies potentially mutating state or submitting data. This contradicts the annotations readOnlyHint set to true. Because the description directly conflicts with the annotation and also provides no safety/auth/side-effect context, this dimension scores minimal.

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 not excessively long, but it repeats the core idea: the first sentence and the 'Finally it returns...' sentence both say the tool returns data in a specified format. Some sentences are redundant rather than adding new operational guidance.

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 output schema and detailed input-schema provide substantial structure, so this is not a sparse definition. However, the description misses important behavioral context around a browser automation tool, such as side effects from form submission, authentication state, and session behavior; this is made worse by the annotation contradiction.

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 already covers all parameters with descriptions at 100% coverage, so the baseline is 3. The description repeats the conditional schema requirement for json/csv/toon and explains task_prompt, but it adds no new information beyond what the schema provides.

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 says 'Run the browser agent and return the data' and then lists concrete actions like clicking, filling forms, scrolling, and navigating to URLs. This gives a specific verb/resource and conveys an interactive browser tool, though it does not explicitly name or contrast sibling scraper/crawler tools.

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 says the tool is 'useful if you need navigate around the website and do some actions,' which implies an interactive task. However, it provides no explicit guidance on when not to use it or which sibling tool (e.g., ai_scraper, ai_crawler) should be used for static extraction.

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