scrape_page

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint. Description adds critical context: content capped at max_length, truncation flag, mode preview forces 5000 bytes, concurrent scrape limit, caching behavior, and error handling with isError and reason field. No contradictions.

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?

Description is fairly long but well-structured: starts with core purpose, then covers supported formats, fallback strategy, return fields, constraints, and alternatives. Every sentence adds value; could be slightly more concise but not excessive.

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 tool complexity (multiple content types, modes, fallback, concurrency, caching, error handling, output schema), description covers all essential aspects. Output schema exists but description still explains return fields and behavior (truncation, estimated tokens, citation format). No missing context.

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%, but description adds meaning: explains URL supports multiple document types and YouTube, mode explains preview forces 5000 bytes, max_length describes default 50000 and suggests use for faster responses. This goes beyond schema descriptions.

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?

Description clearly states 'Extract readable content from a single URL' and lists supported content types (HTML, JS-rendered SPAs, PDFs, DOCX, PPTX, YouTube transcripts) and extraction methods. It distinguishes from siblings like search_and_scrape and web_search.

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?

Explicitly provides when to use alternatives: 'Use search_and_scrape instead to discover and extract in one step; use web_search if you only need URLs.' Also mentions concurrency limit (max 5) and caching (1 hour), guiding effective use.

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