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

With no annotations, the description carries the full burden and does so excellently. It discloses recursive behavior, irreversibility with no trash, refusal of storage roots, and error-on-missing-path semantics. This is exactly the safety-critical context an agent needs.

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 well-structured sentences, each earning its place: operation and counterpart, irreversibility, and safety/error behavior. There is no filler, and the most important information is front-loaded.

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 unannotated, destructive tool with no output schema, the description covers operation scope, irreversibility, protected paths, and failure behavior. It is complete enough for an agent to invoke the tool correctly and avoid common mistakes.

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 100%, so the baseline is 3. The description adds useful context around path safety (root refusal, empty-variable mistakes) but does not add direct parameter-level meaning beyond what the schema already provides for udid and remotePath.

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: 'Delete a file or directory on the device (recursive).' It also identifies itself as the counterpart of ios_file_delete, which clearly distinguishes it from the iOS sibling. The operation and scope are unambiguous.

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?

Names the sibling counterpart (ios_file_delete), making the platform-based alternative clear. It also provides strong when-not guidance by explaining that storage roots are refused and why. However, it does not explicitly phrase 'use this when deleting on Android' as a direct selection rule, so it stops short of a 5.

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