find_elements

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

With no annotations provided, the description carries the full behavioral burden, and it delivers. It discloses that element handles resolve immediately into JSON-like dictionaries, that live SeleniumBase objects are not returned, and that element handles cannot be persisted across MCP calls. It also specifies the exact return shape and empty-result behavior, which is valuable beyond the bare schema.

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 well structured with clear sections: summary, args, returns, tool selection, and a note on handle persistence. Every sentence adds useful information, and the most important distinction from sibling tools is front-loaded. The length is justified by the absence of annotations and schema-level parameter descriptions.

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?

The definition covers the tool's purpose, when to use it versus alternatives, all parameter semantics, the return structure, and the key limitation that element handles cannot persist across MCP calls. This is everything an agent needs to correctly select and invoke the tool, even without annotations.

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 input schema provides only names, types, and defaults, with 0% schema description coverage, so the description must compensate. It does so thoroughly by explaining selector syntax with concrete examples, defining timeout as maximum wait seconds with its default, and describing exactly what include_html controls. This adds real meaning beyond the structured schema.

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 opens with a precise verb and resource: 'Find matching elements and return structured element information.' It also explicitly distinguishes itself from siblings in the Tool selection section, naming get_content, click, and check_condition as alternatives, so an agent can easily tell what this tool is for.

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 Tool selection section gives concrete when-to-use guidance: use find_elements for structured information about matching elements, get_content for page/single-element text/HTML, click with nth for clicking one match, and check_condition for presence/visibility. This is explicit and actionable, leaving no inference required.

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