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

No annotations are provided, so the description carries the burden. It discloses the required input encoding (base64), the decoded size hard cap of 20MB, allowed destination roots, the restriction on shell metacharacters, and the return payload shape. It does not state side effects like overwriting existing files at remotePath or permission requirements. This is a meaningful gap but the description is far above the 2-point floor for unannotated mutation tools.

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 compact and front-loaded. Every sentence carries information: what to push, where allowed, size limit, shell metacharacter constraint, sibling preference, return shape. No filler or repetition of schema text.

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 three-parameter tool with 100% schema coverage and no output schema, the description covers the operational constraints (destinations, size, encoding, safety) and return shape. It does not mention overwrite behavior or file permission implications, which would be valuable for an agent, but given the schema carries parameter definitions, the description is close to 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 description coverage is 100%, so the baseline is 3. The description adds value over the schema by specifying that content is base64 strings, that remotePath must be absolute and start with allowed roots, and that the decoded size cap applies. That justifies a 4 rather than a 3, since it clarifies format and constraints not present in the schema 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 description uses a specific verb and resource: 'Push a base64-encoded file to the device.' It clearly states the allowed destinations and the return shape. It distinguishes from siblings like device_file_pull, device_file_copy, and app_install. Sibling differentiation is explicit with 'For APKs, prefer app_install instead.'

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-use context and an explicit alternative: 'For APKs, prefer app_install instead.' It also states constraints (destinations, size cap, no shell metacharacters) that tell an agent when this tool is appropriate. This exceeds the baseline by naming the sibling condition.

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