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

Annotations already declare non-readOnly, openWorld, non-idempotent and non-destructive, so the description doesn't repeat safety. It does add real behavioral context beyond them: state persistence across actions and the fact that navigation alone doesn't yield content, so a wait/get_html step must follow. It stops short of saying what the call returns or what happens on failure.

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 dense sentences with zero filler: the primitive's identity and state-persistence trait come first, the alternative second, the required follow-up third. 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?

For a one-parameter low-level primitive with a free-form nested options object and no output schema, the description covers the essential lifecycle: navigate, then wait or read HTML. The remaining gap, return value and error behavior, is modest but real for a stateful open-world 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 coverage is 100%, so both the single 'options' property and its nested-object nature are already documented. The description restates that options is EngineRequestOptions with url and wait, adding no syntax, defaults, or format details beyond the schema. Baseline 3 applies when the schema does the work.

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 specific verb+resource ('low-level navigation primitive') and its key differentiator: it keeps browser state across multiple actions. It names importio_web_fetch as the alternative for single-page fetches. It does not, however, distinguish itself from the closely-named sibling importio_action_goto, leaving ambiguity for an agent scanning the sibling list.

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 an explicit when-not ('for single-page fetches, use importio_web_fetch') and prescribes follow-up calls (importio_action_wait_for_selector or importio_get_html). What's missing is guidance against importio_action_goto, which appears to be a near-equivalent high-level action.

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