page_upload

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

With no annotations provided, the description carries the full burden of behavioral disclosure — and it largely delivers: it discloses the mechanism (set directly on the element, bypassing the OS picker), the input constraint (absolute paths readable by this process), and the post-action behavior (reports network/console/url delta). It does not cover failure modes (e.g., unmatched selector or non-file input), which keeps it below 5.

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 sentences, each earning its place: the core operation is front-loaded, the path constraint is stated baldly, and the return behavior is captured. No fluff and no restatement of schema content.

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 5-parameter tool with no annotations and no output schema, the description covers the essentials an agent needs: what the tool does, how to target the element, the path requirement, and what the call returns. Remaining gaps are sessionId semantics and error behavior, which are secondary for correct invocation.

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 description coverage is only 40%, and the description compensates for the two most ambiguous parameters: 'by ref from page_snapshot, or CSS selector' explains ref and selector, which have no schema descriptions, and it reinforces the files absolute-path requirement with 'readable by this process.' waitMs is already covered by the schema; only sessionId remains undocumented in both.

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 specific verb and resource ('Attach file(s) to a file <input>') and adds the OS-picker analogy, making the operation unmistakable. This tool's upload/attach function is unique among the sibling set — no other page_* or net_* tool covers file attachment — so there is no ambiguity about when it applies.

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 OS-picker equivalence ('the equivalent of choosing files in the OS picker') is clear context for when to use this tool, and the targeting options ('by ref from page_snapshot, or CSS selector') guide how to invoke it. However, the description names no alternatives or when-not-to-use conditions, which keeps it from a 5.

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