Auto-Browser

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

With no annotations provided, the description carries the full burden. It adds valuable return structure details ({text, links, images, y_position}) since no output schema exists. However, it omits safety/performance traits (rate limits, whether scrolling loads more content, visibility constraints) that annotations would typically cover.

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 with zero waste: first defines the action (scrape visible posts), second defines the return structure. Every word earns its place. Front-loaded with the verb and appropriately sized.

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 2-parameter scraping tool without annotations or output schema, the description partially compensates by documenting the return structure in text. However, the complete lack of parameter documentation (0% schema coverage with no description compensation) leaves a significant gap. Minimum viable but clear room for improvement.

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 0% (neither session_id nor limit have descriptions). The description fails to compensate—it mentions 'current page' which loosely implies the session concept but provides no guidance on the 'limit' parameter's usage or the required session_id format. Critical gap given the schema provides no documentation.

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 uses specific verb 'Scrape' with resource 'feed posts' and scope 'current page', clearly distinguishing it from sibling social.extract_profile (which handles profiles, not posts). However, it doesn't explicitly identify the social media/browser context that would make the distinction from social.search obvious.

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?

No guidance provided on when to use this versus social.search (query-based) or social.extract_profile. No prerequisites mentioned (e.g., needing to navigate to a feed page first). The description assumes the agent already knows the tool relationships.

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