crawl_site

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

With no annotations provided, the description carries full responsibility for disclosing behavior. It explains the crawling and chunking process, two modes, and confirms that it returns structured JSON. However, it does not detail the exact structure of the return JSON (e.g., field names), which is a gap in transparency. The warnings about confirmation and credit usage add valuable behavioral context.

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 well-structured with a front-loaded summary, followed by distinct sections for mode differentiation, warnings, and a pre-flight sequence. It is longer than necessary but each sentence serves a purpose, and the organization helps the agent parse key information quickly. A slight reduction in length could improve conciseness without losing clarity.

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 the tool's complexity (11 parameters, 1 required, no output schema), the description covers usage, modes, warnings, and a complex workflow (contextual retrieval pre-flight). However, it does not describe the output format or error handling, which are important for a complete understanding. The absence of an output schema means the agent must infer the return structure, leaving a minor gap.

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 baseline is 3. The description adds little beyond the schema: it reiterates the two modes and the max_pages default but does not provide new insights for parameters like 'selector', 'exclude_pattern', or 'include_pattern'. The schema already has adequate descriptions, so the description offers marginal additional value.

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 crawls an entire website, chunks pages, and returns structured JSON. It specifies two modes ('sitemap' and 'spider') and distinguishes itself from the sibling tool 'extract_crawl' by noting that this tool is for obtaining chunks from multiple pages without structured field extraction.

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 provides explicit when-to-use and when-not-to-use guidance: use for multiple pages without structured fields, use 'extract_crawl' for structured extraction. It also includes practical warnings (confirm max_pages, warn about credit usage) and a pre-flight sequence for contextual retrieval, making it easy for the agent to decide and invoke correctly.

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