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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds a genuinely decision-relevant trait beyond that: the call is synchronous and returns immediately, so an agent knows not to poll.

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?

Two tightly packed sentences, no filler, with the core action front-loaded and the behavioral note second. Every clause 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?

With no output schema, the description carries the return-value burden and only says 'returns the result immediately'. Nothing about failure modes, timeouts, geo settings, or how the two extraction modes interact — gaps that matter for a generic extraction tool.

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 maps loosely to the 'instructions' and 'extract_schema_json' parameters, but says nothing about the nested settings.country_code field (which has no schema description) or how instructions and schema combine when both are supplied.

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?

States a concrete verb+resource: loads a webpage by URL and extracts structured data from it. It distinguishes itself implicitly from the hundreds of site-specific run_* scrapers by being URL-generic, but never explicitly says so.

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 'and/or a JSON schema' phrase hints at two operating modes (instruction-driven vs schema-driven), which is mildly decision-useful. However, it gives no when-to-use vs alternatives, no mention that it is the fallback for arbitrary URLs rather than a site-specific sibling, and no exclusions.

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