extract

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

Annotations declare readOnlyHint=true and openWorldHint=true. The description adds context about anti-bot bypass (stealth), per-domain rate limiting in batch, and crawl depth behavior. It does not contradict annotations. However, it could disclose more about potential side effects (e.g., rate limits on interact sessions) but overall provides good behavioral coverage beyond annotations.

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 long but well-structured with headings, bullet points, and examples. It front-loads the primary purpose and action list. Some redundancy (e.g., repeated 'example:' patterns) could be trimmed, but the organization aids readability and scanning. It is appropriately sized for the tool's complexity.

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 17 parameters and 8+ actions, the description covers major actions and their parameter dependencies. It references the `help` tool for full documentation, acknowledging its own limits. An output schema exists, so return value explanation is not required. Missing detailed handling of some parameters (e.g., prompt, format) but overall completes the picture for typical use cases.

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?

Input schema coverage is 0%, so the description must compensate. It explains required parameters per action (e.g., urls, paths, query, actions) and describes key optional parameters like depth, max_pages, stealth. It clarifies defaults and constraints (e.g., max_urls hard cap 20). Not all parameters are covered (e.g., prompt, format) but the description adds significant meaning for most critical parameters.

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 primary function: 'Read and return full page content from URLs or local files.' It then enumerates distinct actions (extract, batch, crawl, map, convert, etc.), each with specific verbs and resources, and contrasts with the `search` sibling tool for finding URLs. This provides excellent differentiation.

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?

Explicit when-to-use and when-not guidance is provided: 'Use this when you have a specific URL and need its content. For finding URLs first, use the `search` tool instead.' Each action includes example usage scenarios and parameter requirements, offering clear decision support.

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