LionScraper

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

With no annotations provided, the description carries full behavioral disclosure burden and succeeds well. It reveals extension-side rate limiting (500ms minimum, max 3 concurrent tabs), WebSocket bridge mechanics ('bridgeTimeoutMs', 'EXTENSION_NOT_CONNECTED' handling), processing pipeline (deduplication and filtering happens in-extension), and DOM requirements ('logged-in session cookies, JS-rendered content'). Minor gap: doesn't explicitly state read-only nature, though implied by 'scan'.

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?

Uses clear markdown headers (### Purpose, ### When to use, etc.) creating scannable structure. Front-loaded with critical operational prerequisites (ping, lang). While lengthy due to 12 complex parameters and WebSocket architecture explanations, every section earns its place by providing necessary operational or behavioral context not found elsewhere.

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 high complexity (12 params, nested objects, WebSocket extension) and lack of output schema, the description adequately covers return values ('MultiUrlResult; success data is string[]'), error handling patterns (ping/retry logic), and parameter interactions. Could marginally improve by enumerating specific error cases in the return structure, but sufficiently complete for agent operation.

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 100%, establishing baseline 3. The description adds usage context beyond schema: specifically when to use 'zh-CN' ('Chinese users pass lang: zh-CN'), explains the relationship between concurrency/scrapeInterval and extension limits ('extension enforces...'), and clarifies that bridgeTimeoutMs is server-side only ('Stripped before forwarding'). This lifts it above baseline schema repetition.

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 explicitly states 'Scan HTML for email addresses, dedupe, optional domain/keyword/limit filters,' providing a specific verb (scan), resource (HTML/email addresses), and scope (deduplication/filters). It clearly distinguishes from siblings like scrape_article or scrape_images by specifying the email extraction use case.

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?

Contains explicit 'When to use' section ('Contact/about/footer pages when the user wants an email list') and strong negative guidance against alternatives ('Do not substitute raw HTTP... do not use WebFetch, curl, wget'). It also specifies prerequisite workflow ('Call ping first') and chaining patterns ('Often chained after scrape_urls'), giving complete decision-making context.

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