browser_extract

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

No annotations are provided, so the description carries full burden. It explains the two return paths (markdown string vs. object with path/chars) and mentions the output_path behavior. However, it lacks details on prerequisites (e.g., page must be loaded), error handling, or limits on page size/token efficiency. The behavioral disclosure is adequate but not comprehensive.

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 a single, well-structured paragraph that front-loads the core action. Every sentence adds value: the extraction purpose, the output format, the optional output_path behavior, and the agent's subsequent role. It is slightly verbose with the agent guidance, but overall efficient for the complexity.

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?

Given no output schema, the description adequately explains both return types. However, it does not cover edge cases (e.g., empty page, non-HTML pages, or errors) or prerequisites like a valid browser session. The context is sufficient for straightforward usage but misses important situational details.

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 coverage is 0%, meaning the description must compensate. It explains the effect of output_path (write to file and return object vs. return string) but does not mention session_id or its purpose. For a two-parameter tool, partial coverage (one parameter explained) is insufficient to warrant a higher score; baseline for 0 params would be 4, but with gaps a 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 clearly states it extracts the current page as clean, token-efficient markdown. The verb 'Extract' combined with the specific resource 'current page' and format 'markdown' makes the purpose unambiguous. It distinguishes from sibling tools like browser_snapshot (image) and browser_evaluate (JS execution) by specifying the exact output format.

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 implies usage as a first step for extractions, noting the agent does further structuring. However, it does not explicitly state when to use this tool versus alternatives like browser_snapshot or browser_evaluate. There is no exclusion guidance or comparison to siblings, leaving the agent to infer from context.

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