Crawl Website

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

The description discloses '1+ credits per page' and explains the blocking behavior when wait=true and the job id return when wait=false, adding cost and async context beyond the readOnlyHint annotation. This provides valuable operational details without contradicting the 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 two sentences, efficiently covering purpose, output, cost, and wait behavior. Every sentence carries essential information with no fluff, and the primary action is front-loaded.

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?

For a 6-parameter tool with no output schema, the description covers the core operational aspects: markdown output, credit cost, wait behavior, and job id reference. It lacks details on the exact structure of the returned markdown, but annotations and full schema coverage fill most gaps, making it sufficient for an agent to invoke correctly.

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?

With 100% schema description coverage, the baseline is 3. The description adds meaning for the wait parameter by specifying that wait=false returns a job id for metalift_job_status, which is not in the schema. Other parameters are sufficiently described in the schema.

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 'crawl a site from a seed URL and return markdown for discovered pages,' which uses a specific verb ('crawl') and resource ('site') and distinguishes it from single-page scraping tools. The mention of discovered pages plus the cost per page adds unique functionality compared to siblings.

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 context about the wait parameter and references metalift_job_status for asynchronous usage, but it does not explicitly state when to choose crawl over alternative tools like metalift_scrape, metalift_sitemap, or metalift_map. Usage is implied rather than clearly differentiated.

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