tweak

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false; the description adds a meaningful claim that tweaks are 'reversible', which explains why destructiveHint is false. However, it does not describe the approval/preview gate (owner_approved) that governs whether the call mutates the device, nor failures, persistence, or whether existing settings are overwritten, so it adds only partial behavioral context beyond the annotations.

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 packed sentence that front-loads the key qualifiers ('named', 'reversible') before the catalog. Density is high and nearly every token carries information, though the long private-dns enumeration slightly crowds out the higher-value usage and approval context.

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 4-parameter mutation tool with no output schema, the description covers the name/args vocabulary well but leaves the agent without the preview-versus-apply flow, device targeting behavior, or what a call returns or does on partial failure. Combined with annotation-covered safety hints, this is adequate but not 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 coverage is 50% (device and owner_approved documented; name and args undocumented), and the description compensates well by enumerating legal name values and the argument syntax for each: scale values for animations, the yes|no|auto set for dark-mode, a host-or-provider set for private-dns, and package arguments for the notification and background-restriction tweaks. It does not explicitly map these to the args array, but the '<...>' placeholder notation makes the mapping recoverable.

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 specific resource (a named tweak) as an enumerated catalog of supported tweak names and their argument forms, so an agent knows exactly what operation is performed and what values are legal. It does not distinguish itself from adjacent siblings such as preferences_write, change_packages, or change_permission, so the agent must infer boundaries from the names alone.

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 only implied: the enumerated name list effectively scopes when this tool applies. There is no explicit when-not guidance, no mention of how it relates to undo/restore_everything, and no statement of prerequisites (a connected phone, adb), leaving the agent to infer routing from the tweak catalog.

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