scrape_url

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

With no annotations, the description carries full burden. It discloses chunking behavior, cost (surcharge for js_render, ~$0.001/chunk for contextual retrieval), prerequisite steps (verify_provider_key), and important flags (js_render for SPAs). However, it omits output format details, error handling, rate limits, or caching behavior, which would increase transparency for a tool with 9 parameters.

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 concise in the first paragraph but includes a detailed multi-step pre-flight sequence that, while informative, makes it longer than necessary. Every sentence serves a purpose, but the pre-flight instructions could be more succinct. Overall structured logically: purpose, usage, special case.

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 9 parameters, no output schema, and moderate complexity. The description covers the main use case and the contextual retrieval flow. However, it does not describe the return format (e.g., array of chunks with text, metadata) or error handling. Without output schema, the agent needs more detail on what to expect. Given the richness of the description for the main flow, it's adequate but not complete.

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 baseline is 3. The description adds value by explaining when to use js_render (JavaScript-heavy pages, SPAs), that llm_model must come from verify_provider_key, and that llm_api_key can be an env var. The pre-flight sequence for contextual_retrieval adds operational context beyond schema. However, some schema descriptions already suffice, limiting extra contribution.

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 scrapes a single URL, chunks it into RAG-ready segments, and returns structured chunks. It distinguishes from sibling tools like extract_data (which extracts structured fields) and crawl_site (which does multiple pages). The verb 'scrape' and resource 'single web URL' are specific and unambiguous.

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 states when to use: 'when the user wants to read, summarize, or process content of a specific web page WITHOUT extracting structured fields.' Provides a detailed pre-flight sequence for contextual_retrieval. Does not explicitly list when not to use, but the positive criteria imply exclusion of structured extraction. Sibling names provide context, but description could be more explicit about alternatives.

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