clone

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

Annotations declare this is a write operation that is not destructive and not open-world, so the safety bar is partly met by structured data. The description adds useful scope detail by listing exactly what gets copied (changes, notes, keep list, home screen). It omits the most consequential behavioral fact — that the call is a two-phase preview/apply flow gated on `owner_approved` — which only appears in the schema, and it does not say what happens to settings on the target that are not in the source profile.

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?

A single front-loaded sentence with the destination phone first and the copied items after, plus an inline pointer to `phones`. Nothing is padded or redundant, though the parenthetical reference interrupts the enumeration slightly.

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?

There is no output schema, so the description carries the burden of explaining what the agent gets back — and it does not say what a preview or result looks like. For a multi-field write tool that overwrites launcher/home-screen state, missing notes on overwrite behavior and on the preview-then-approve requirement leave real gaps, even though the copied-field list is a solid start.

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 67%: `device` and `owner_approved` are documented in the schema, while the required `from` parameter has no schema description at all. The description partially compensates by directing the agent to `phones` as the source of that value, but it does not specify the expected identifier form (name vs index vs serial) for `from`. This is roughly baseline-plus, not a meaningful enrichment.

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 states a concrete action ('set this phone up like another saved phone') and enumerates what is transferred: changes, notes, keep list and home screen. It also names the sibling `phones` as the source of the saved profile, so the agent can separate it from unrelated siblings such as `tweak` or `reapply`. The generic name 'clone' is rescued by the description, though the source/target distinction ('this phone' vs the saved phone) could be stated more explicitly.

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?

Usage is implied rather than stated: pointing at `phones` tells the agent where to obtain a valid source profile, which is real routing guidance. However, there is no explicit when-to-use versus `restore_everything`, `reapply` or `playbook`, and no statement of prerequisites such as the target phone being in a compatible state.

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