LionScraper

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

With no annotations provided, the description carries substantial behavioral disclosure: it explains the WebSocket bridge infrastructure, server-side parameter stripping (bridgeTimeoutMs), extension-side constraints (max 50 URLs, min 500ms interval, max 3 concurrency), and content script execution differences from email/phone scrapers. It lacks only an explicit declaration of the read-only/non-destructive nature of the operation.

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?

While organized with clear markdown headers, the description front-loads operational warnings ('### Call ping first') before stating purpose, and the total length is substantial. Every section contains valuable information for a complex 12-parameter tool requiring browser extension infrastructure, though tighter integration could reduce the prerequisite verbosity.

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 the absence of output schema and annotations for a complex tool with nested objects and infrastructure dependencies, the description appropriately covers return types (MultiUrlResult with image record arrays), error handling patterns, retry logic, and BCP-47 language support. It provides sufficient context for successful invocation despite missing explicit safety classifications.

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?

With 100% schema coverage establishing a baseline of 3, the description adds significant semantic value by clarifying the distinction between top-level scrollSpeed and waitForScroll.scrollSpeed, explaining server-only parameters removed before forwarding, and providing usage context like 'drops small icons' for minWidth and 'late-rendered DOM' for delay.

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 'List images (src, alt, size, format, …) with optional filters,' specifying both the action and extracted fields. It effectively distinguishes from siblings like scrape_emails and scrape_article by targeting image assets specifically. However, this purpose statement is buried beneath extensive operational prerequisites, diminishing immediate clarity.

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?

Excellent explicit guidance provided: mandates calling ping first with detailed error handling for EXTENSION_NOT_CONNECTED, specifies exact use cases ('Asset audits, galleries, lazy-loaded pages'), and clearly defines when NOT to use the tool versus alternatives ('Do not substitute raw HTTP...Only if the page is fully public and mostly static').

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