change_packages

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds genuinely useful context that the removal is per-user and reversible, which softens the destructive hint. However, it omits the critical two-step preview-then-owner_approved workflow, so the most important behavioral trait is left to the schema description of a single field.

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 zero filler, and the parenthetical qualifier is placed immediately after the operation it modifies. It is efficient, though its brevity comes at the cost of the workflow detail noted elsewhere.

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, mutating tool with no output schema, the description says nothing about the preview/approval requirement, what happens to app data on removal, or how to reverse the change afterwards. It relies on the agent reading the owner_approved field description to discover the safety gate, which is too much to leave implicit for a destructive operation.

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?

With schema coverage at 50%, the description compensates by explaining what each enum value of the required 'action' parameter actually does, including the reversibility of 'remove' and the meaning of 'enable'. The 'packages' array and 'device' parameter are left to the schema, but their names are self-describing.

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 names three specific operations (disable, remove, re-enable) against a specific resource (packages), matching the action enum exactly. It is clear what the tool does, though it never names a sibling (keep_packages, apply_plan, undo) to distinguish itself from them.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no routing to alternatives like plan_debloat, apply_plan, keep_packages, or undo/restore_everything, which all touch the same package state. The only usage-relevant hint ('for this user, reversible') is embedded parenthetically rather than framed as guidance.

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