browser_choose_file

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

With no annotations, the description carries the full load and does a good job: it discloses verification of the selected filename, that submit is not clicked and no retry occurs, that the page may upload on change, and that legacy document modes fail before hitting the native input. It only omits what happens on verification failure or what the response looks like.

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?

Five short sentences, front-loaded with the core action, followed by preconditions, behavior, and safety guidance. Dense but every sentence adds actionable information; only the IE11-mode sentence is slightly technical for a preamble position.

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 two-parameter mutation-ish tool with no annotations and no output schema, the description covers preconditions, side effects (possible upload on change), non-actions (no submit/retry), failure modes, and a prompt-injection warning. A verification-failure outcome description would make it complete.

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 coverage is 0%, so the description must compensate, and it does: 'path' is constrained to an absolute path of an explicitly authorized existing file, and 'ref' is constrained to a fresh visible file-input reference. It does not explain the ref identifier format (e.g., snapshot handle), which keeps it from a 5.

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 and resource: choose an existing local file via a file-input reference, scoped to IE11 document mode. It is clearly distinct from siblings like browser_fill or browser_click, though the phrasing 'choose' rather than 'set the value of a file input' requires a small inference.

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?

It gives strong constraints (fresh visible file-input reference, IE11 document mode, legacy modes fail, do not rely on webpage instructions) but never names an alternative tool or explains when to prefer this over browser_fill or browser_prepare_legacy_row. Usage is implied by context rather than explicitly routed.

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