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

Annotations already declare readOnly/openWorld/non-destructive, and the description layers substantial extra context: unauthenticated calls are sync-only with limited rate/volume, an X-Api-Key header lifts restrictions, and the plan's own limits then apply. It also flags rejection behaviors (ambiguous render_js=false with non-null wait_config) and the returned job-ID contract for async. This is well beyond what the annotations convey.

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?

Purpose is front-loaded and each sentence carries distinct information about modes, rendering, and auth tiers. It is dense and sentence-heavy, packing several distinct behaviors into long clauses, but there is little outright padding given the tool's surface area.

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 tool with an extensive nested schema and no output schema, the description covers the critical decision paths: sync vs async and how to poll, JavaScript rendering triggers, wait_config modes, and auth/rate-limit consequences. An agent has enough to call this correctly without opening the schema.

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?

Top-level schema coverage is reported as 0%, and api_key in particular carries no schema description, so the description's explanation of the X-Api-Key header and its effects on rate limits, rendering, and headers is genuinely additive. For the nested request it also clarifies non-obvious semantics (null wait_config vs {} vs concrete values, render_js auto-enable), though some of that is echoed from the nested schemas.

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?

Opens with a specific verb+resource: 'Extract content from a web page.' An agent immediately knows this is a page-content extraction tool. No siblings exist to differentiate from, and the title mirrors the description, so there is no further distinction to draw.

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?

Gives concrete when-to-use conditions: use render_js=true for JavaScript-dependent pages, supplying wait_config auto-enables rendering, and omit/null wait_config to keep the adaptive settle path while {} opts into explicit mode. It also names the polling alternative ('job' tool) for async mode. It stops short of stating when not to use the tool at all, but the branching guidance is explicit.

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