Upload file

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

No annotations are provided, so the description carries the full burden, and it discharges much of it: it discloses that no OS picker appears, that CDPM intercepts the picker, and that the site receives the same events as a human file pick. It does not cover failure modes (e.g. invalid path, hidden input, upload rejection), which is the remaining gap.

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, zero filler, and the core behavior is front-loaded before the ref guidance. The final sentence about event fidelity is short and earns its place by explaining the observable effect of the call.

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 an 8-parameter action tool with no output schema, the description covers the one genuinely non-obvious flow (click-then-upload-without-ref) and sets expectations about user-visible behavior. It leaves error handling and any preconditions about the target input unaddressed, but the schema already documents the remaining parameters.

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 100% and each parameter is documented in-schema, so the baseline is 3. The description reinforces the ref/no-ref distinction, but the schema already states 'Omit to use the file picker just opened by a click', so it adds little beyond structured data.

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 ('Puts files into a file input') and immediately clarifies the mechanism ('no OS file picker shown to the user'), which separates it from browser_click and browser_fill. An agent can tell exactly what this tool does 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 the two explicit invocation paths: pass ref for a real <input type=file> or its label, or click a custom 'attach' button with browser_click first and then call without ref. This is a complete when/how decision tree with the alternative tool named.

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