Tap

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

While annotations indicate this is a non-destructive write operation (readOnlyHint: false, destructiveHint: false, openWorldHint: true), the description adds specific behavioral context about error handling mechanisms (toast notifications) and validation constraints (format and size limits) not captured in the structured metadata.

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 consists of exactly two high-value sentences: the first establishes the core action, the second provides critical error-checking instructions. No extraneous information is present, and the content is appropriately front-loaded.

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?

Given the lack of output schema and 0% parameter description coverage, the description adequately covers the high-level operation and error handling but leaves significant gaps regarding parameter semantics. It meets minimum viability but requires the consumer to infer parameter formats from the tool name alone.

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?

With 0% schema description coverage, the description fails to compensate by documenting the expected format for the 'files' parameter (file path, base64, JSON array?) or clarifying that 'selector' targets a DOM file input element. The phrase 'file input' only weakly implies the selector's target without explicit parameter mapping.

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 clearly states the specific action (upload) and target resource (files to a file input), distinguishing it from sibling interaction tools like tap_click or tap_type. However, it assumes familiarity with what constitutes a 'file input' without specifying it refers to an HTML/DOM file input element.

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 description provides valuable post-action guidance to check inspect.toasts for specific error types (wrong format, size limit), implying a validation pattern. However, it lacks explicit guidance on when to choose this over alternatives or prerequisites like element visibility.

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