list_changes

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

The annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is carried by structured data and the description need not repeat it. The description does add that the listing is device-scoped and that returned records carry undo-usable ids, but it says nothing about ordering, volume/limits, or the scope of 'every' for a long-lived device.

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 clause-sized sentence with zero filler, front-loading the scope ('every change made to this phone') before the payload note. Nothing redundant is present and nothing obvious is over-explained.

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 bears some responsibility for what a returned change record looks like, and it gives only 'ids for undo'. Combined with an undocumented 'include_undone' parameter, an agent cannot confidently predict whether the default call surfaces reverted changes or how to interpret results.

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 description coverage is 50%: 'device' is documented inline, but 'include_undone' has no description anywhere. The description does not clarify that flag at all — critically, whether undone changes are excluded by default — leaving an agent to guess the default behavior of a filter that materially changes the result set.

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 the resource (every change made to the phone) and the returned payload (ids for undo) precisely enough that an agent knows this is a device-wide change-history listing. It does not distinguish itself from plausible siblings such as 'drift' or 'undo', which is why it stops short of 5.

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?

'with ids for undo' implies the downstream workflow (list changes, then call undo with a returned id), which is genuine but implicit usage guidance. There is no explicit statement of when to prefer this over 'drift', 'undo', or 'report', and no exclusions.

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