Sideload Channel Package

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

The description explicitly discloses that it replaces any currently sideloaded Dev App and flags it as not safe for autonomous use, matching and contextualizing the destructiveHint=true annotation. It additionally reveals the temp-file write/cleanup lifecycle for contentBase64 and the actionable error for sandbox-looking filePath values — all behaviors beyond what annotations provide.

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 long but every sentence earns its place. It front-loads the purpose and destructive warning, then clearly structures the two input modes with their caveats. There is no filler; each sentence adds unique operational information.

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 destructive action with two input modes, optional password, no output schema, and five parameters, the description covers everything needed to invoke it safely: what it does, what it destroys, the exact conditions for each input mode, temp-file cleanup, password behavior, and error handling. Nothing critical 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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful decision-making context: mutual exclusivity of filePath and contentBase64, the same-machine requirement for filePath, the temp-file write/delete flow for contentBase64, and the 'omit if remembered' rule for password. These details go well beyond the schema's field descriptions.

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 first sentence uses a specific verb ('Upload and install') and resource ('.zip channel package on the device'), making the core action unambiguous. It also surfaces the destructive replacement behavior, which helps differentiate it from non-destructive tools. However, it does not explicitly name sibling tools like delete_sideload or launch_app, so it stops short of a 5.

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 gives explicit when-to/not-to-use guidance: it warns against using filePath in a remote agent sandbox and directs agents to contentBase64 when no shared filesystem exists. It also states that the tool is 'not safe for autonomous use without user intent,' acting as a clear exclusion condition. This is exemplary usage guidance.

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