extract_form_fields

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

With no annotations, the description carries the full burden, and it does disclose the shape of the return (label, type, options, CSS selector for filling) and the scoping constraint that only visible fields are returned. It is implicitly a read-only operation with no mutation risk, but it does not describe behavior when the page has no forms or is not yet loaded.

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?

Three short sentences, each earning its place: purpose, return shape, prerequisite. The prerequisite is placed last as a call-to-action, and nothing is redundant.

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?

There is no output schema, so the description correctly compensates by naming the returned fields, and it supplies the required setup step. It falls just short of complete by not covering the empty-page or unopened-page failure modes an agent might encounter.

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?

The tool takes zero parameters, so there is nothing for the description to document and the baseline of 4 applies. No semantic gap exists to compensate for.

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 ('Extract') and resource ('all visible form fields from the current page'), with the scope qualifier 'visible' and 'current page' narrowing it precisely. The verb is clearly distinct from the mutation siblings fill_form_field and select_form_option, so an agent can pick it without opening the schema.

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 prerequisite: 'Call open_application_page first,' which establishes the ordering relative to a named sibling. It does not state exclusions or alternatives (e.g., when to prefer fill_form_field next), so it stops short of full when/when-not guidance.

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