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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it bypasses Cloudflare Turnstile and anti-bot mechanisms, uses AI Multimodal Vision, and is optimized for LLM context windows and RAG pipelines. This goes beyond the annotations and helps the agent understand the tool's capabilities and limitations. It doesn't mention rate limits or potential failures, but the added context is substantial.

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 two sentences with zero waste. It front-loads the core purpose, then adds the key differentiators (bypassing anti-bot, no CSS selectors, token-optimized). Every sentence earns its place, and the marketing-style language is efficient.

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 tool has an output schema, so return values are covered. The description explains the input parameters well through the schema, and the behavioral context (bypassing anti-bot, using vision) is sufficient for an agent to decide whether to use it. It doesn't mention edge cases like non-JavaScript pages or paywalls, but for a scraping tool with this complexity, the description is complete enough.

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 100%, so the schema already documents all three parameters. The description adds context about the extraction_query being natural language instructions and the response_schema enforcing structured output, but it doesn't add significant new meaning beyond the schema. Baseline 3 is appropriate since the schema does the heavy lifting.

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's function: extracting structured, token-optimized data from live web pages using AI Multimodal Vision. It names the specific resource (live web page) and the action (extract structured data), and distinguishes itself from brittle CSS selectors. The sibling tool phishvision_detect is different enough that this description makes the purpose clear.

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 when to use this tool: when you need to extract data from a live web page, especially one protected by anti-bot mechanisms or dynamic JavaScript rendering. It doesn't explicitly state when not to use it or name alternatives, but the context is clear. The sibling tool phishvision_detect is not mentioned, so no explicit exclusion is given, but the use case is well-defined.

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