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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds the behavioral nuance that extraction is AI-powered and returns structured data based on the 'type', which adds value beyond annotations. It does not discuss potential errors, latency, or API key requirements beyond the parameter, but given annotation coverage, 3 is appropriate.

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 and efficient, packing core purpose, type options, and an example into two sentences. It front-loads the primary action and then provides the example call, which is useful. It could be slightly more structured, but it's appropriately sized with no fluff.

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 that the tool has only 3 parameters, full schema coverage, and no output schema, the description covers the essential usage. It includes an example call and explains the type parameter's effect on return fields. The lack of output schema means the do_not_explain_return_values clause doesn't apply, but the description still gives enough info for an agent to call it correctly. The main gap is explicit mention of when to use this vs sibling tools, but overall it's sufficiently 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 coverage is 100%, so each parameter is described in the schema. The description adds semantic meaning for 'type' by specifying what fields are extracted for each enum value (e.g., 'name, price, currency' for product), which is helpful beyond the schema's simple enum description. However, it doesn't add much for 'url' or '_apiKey' beyond what's already there, so baseline 3 is suitable.

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 function: 'AI-powered automatic extraction of structured data from a web page.' It identifies the specific resource (web page) and action (extract), and distinguishes the two modes (product vs article) with concrete examples of what each outputs. This sets it apart from sibling tools like zyte_fetch or zyte_screenshot, which likely handle raw content or images.

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 clear usage context by explaining when to use 'product' vs 'article' and mentions the default. It also includes an example call with parameters, which helps the agent understand invocation. However, it does not explicitly mention when to prefer this over zyte_fetch or zyte_screenshot, though the structured extraction intent is implicitly distinct.

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