keep_packages

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the agent knows this mutates persistent state non-destructively. The description adds the key behavioral fact that the list means 'never wants touched' (i.e., other operations should respect it) and that entries can be removed. It does not say where the list is stored, whether the change is persisted across devices, or that it makes no on-device changes itself.

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 sentence with a parenthetical that carries real meaning (the remove mode) rather than filler. It is front-loaded with the primary action, with no redundant restatement of the name.

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 low-complexity, 3-parameter mutation tool with no output schema, the description covers intent and the toggle mode, which is the minimum needed to call it. It omits what the agent would most want to know: whether the keep list affects other tools in this family and whether the change persists, leaving the definition only adequate.

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 only 33% (only 'device' is documented), so the description must carry weight — and it does explain 'remove' as the mode toggle for deleting entries and 'packages' as the members of the keep list. It adds no guidance beyond the schema for 'device' scoping or for batching multiple packages, leaving half the gap unfilled.

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 ('Record') and resource ('packages the owner never wants touched'), and the parenthetical clarifies the tool is bidirectional (add or remove from the keep list). It does not differentiate itself from the nearby sibling 'change_packages' or explain how the keep list interacts with 'plan_debloat'/'apply_plan', so an agent must infer the boundary.

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, no prerequisites (e.g., does the owner need to confirm protection changes?), and no named alternative. The only usage signal is the implied 'when the owner wants a package protected' reading of the description.

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