ai_extract

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

Since no annotations are provided, the description carries the behavioral disclosure burden. It usefully reveals that an LLM reads the rendered page and returns JSON, but it does not mention failure modes, latency, cost, nondeterminism, or how the html parameter interacts with url.

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 three concise sentences with no filler: it states the purpose, gives a usage pattern with an example, and explains the mechanism. Key information is front-loaded and every sentence earns its place.

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 3-parameter tool with fully described schema, the description adequately covers the main inputs, the output format, and the general behavior. It does not address edge cases like supplying both url and html, but those are minor given the schema already clarifies html is an alternative.

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%, with each parameter already documented clearly. The description adds an example of a prompt and confirms JSON output, but it does not significantly extend beyond what the schema already provides, so the baseline of 3 is appropriate.

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 verb and resource ('Extract structured data from a web page') and explains the natural-language interface with a concrete example. It doesn't explicitly distinguish itself from sibling extract_page, but the LLM-powered, natural-language mechanism implies a distinct behavior.

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 implies usage by showing the workflow: provide a URL, describe the desired data, receive JSON. However, it gives no explicit when-to-use vs. when-not-to-use guidance and makes no comparison to alternatives like extract_page or render_screenshot.

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