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

Annotations already declare a safe, idempotent, read-only, non-open-world operation, and the description still adds substantial behavioral context beyond them: the concrete failure mode (a JPEG pushed to /DCIM never enters Photos, verified on iOS 26.6 across reboot; the media Downloads folder is not the Files app's Downloads), the meaning of an empty `pickable_from`, and the guarantee that the push still works even when nothing is pickable. This is exactly the extra context the lower annotation bar asks for.

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 actionable instruction (call before ios_file_push, push to targets[0].push_path) is front-loaded and the rest is dense justification. It is longer than typical descriptions, and the parentheticals about iOS 26.6 verification could be trimmed, but nearly every sentence carries information an agent would misuse the tool without.

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?

With no output schema, the description still documents the return shape (`pickable_from` values, `targets[0].push_path`, `advice`), the sort order (pickable first), and the interpretation of each `pickable_from` state. Given a single required parameter and no structured output contract, nothing an agent needs to call and interpret this tool is missing.

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?

Only one parameter (`udid`) and schema description coverage is 100%, so the schema already documents it and the description adds no syntax or format detail. Per the high-coverage rule this sits at the baseline even though the description provides rich semantics for the returned structure.

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 (find where to push a file so a picker can select it) and immediately qualifies the scope to picker-driven uploads in Safari or an app under test. The distinction from the sibling ios_file_push is made explicit and the description makes clear this is a discovery step, not the push itself.

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?

Explicitly says 'Call this before ios_file_push when the file is meant to be chosen by a picker' and supplies the negative case (writing a file and a picker seeing it are not the same thing, so ordinary pushes do not need this). It also explains what to do when no target is pickable via the `advice` field, so the agent has a full when/when-not/next-step path.

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