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

With no annotations provided, the description takes full responsibility for behavioral disclosure. It goes beyond a simple statement by revealing that the shared media directory is writable but not picker-visible, verifying this on iOS 26.6, and explaining the meaning of `pickable_from` values, sorting behavior, and the `advice` fallback. This is rich, actionable context that fully informs the agent about side effects and edge cases.

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 is dense but not overly long; every sentence contributes value. It opens with the core purpose, then provides usage guidance, followed by behavioral and output details. The structure flows logically from what to do, to pitfalls, to how to interpret results. Slight verbosity from the detailed examples is warranted given the tool's complexity.

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 tool's complexity, absence of an output schema, and single required parameter, the description is remarkably complete. It explains return values (`pickable_from`, `push_path`, `advice`), how to act on the result (push to `targets[0].push_path`), why certain paths fail, and what the user should do if nothing is pickable. No critical information is missing for an agent to use the tool correctly.

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?

The only parameter, `udid`, is fully documented in the schema with 'iOS device UDID', giving 100% schema coverage. The description does not add any additional parameter-specific detail beyond implicit reference to the device. Since the schema already covers the parameter semantics, the description's lack of added info keeps this at baseline.

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 uses a specific verb+resource: 'Find where to push a file so a FILE PICKER on the device can select it'. It clearly distinguishes itself from ios_file_push by focusing on picker-visible locations, and even references ios_file_push as the subsequent action. This is unambiguous and differentiates the tool from siblings.

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 explicitly states when to use the tool: 'Call this before ios_file_push when the file is meant to be chosen by a picker'. It also explains why this is necessary, noting that writing a file and a picker seeing it are not the same thing, and gives a concrete example of a common pitfall. This provides clear context and an exclusion criterion for when not to use it.

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