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

Adds substantial context beyond the annotations: full pre-validation with path-qualified errors (apps[1].spec.screens), all-or-nothing installation, and the already_installed failure mode. It also clarifies that Android and iOS styles are preserved. What it omits is whether replace=true destroys the existing app's data or merges it, which matters given destructiveHint=false.

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?

Front-loads the purpose in one sentence, then the validation contract, then failure conditions — good ordering with dense, useful sentences. The final sentence listing invalid_spec/already_installed partially repeats error names already introduced, which is mild redundancy.

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 carries the return-behavior burden and does so by naming error codes and the validation report format. It falls slightly short on the success case — nothing says what is returned after install or whether the existing home-screen layout is replaced or merged.

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 earns an extra point by explaining the functional consequence of replace (duplicate ids fail with already_installed otherwise) rather than just restating 'overwrite'. The apps parameter is tied back to its source in export_phone_apps, though session goes unmentioned.

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 ('Put apps from export_phone_apps on this phone') plus the payload scope: data, settings, and home-screen layout. Referencing export_phone_apps explicitly positions it as the inverse operation, which separates it from siblings like arrange_apps or list_installed_apps.

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?

Makes clear this is the restore counterpart to an export, and gives the decisive condition for the replace flag: an already-installed id fails unless replace is true. It does not enumerate other restore-style alternatives, but the paired-tool framing provides clear context for selection.

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