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

Annotations already declare readOnlyHint and destructiveHint=false, yet the description adds substantial behavioral context: retention bounds (100 changes/250 MB/30 days per caller, oldest dropped first), which change types are tracked (writes, edits, moves, explicit copies), and which are not undoable (shell commands, deletes, untracked/oversized). This is real value beyond the structured fields.

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?

Front-loaded with purpose, then dense, non-redundant sentences covering ordering, change types, retention bounds, and undo exclusions. Every clause carries information an agent needs; nothing is padding.

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?

With no output schema present, the description responsibly states the notable return fields (changeId, undo availability) and ordering. Minor gaps remain around pagination/limit interplay, but coverage is strong for a read-only list tool.

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%; deviceId and workSessionId are documented in the schema itself, while limit is undocumented. The description's 'bounded to 100 changes' loosely relates to limit's maximum of 100 but adds no per-parameter guidance, so this sits at the baseline where the schema does most of the work.

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 (List) and resource (retained file changes in this work session) with scope and ordering, and cites the key output fields (changeId, undo availability). An agent can distinguish it from the write/mutation siblings like write_file or undo_file_change immediately.

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?

The description implies when to reach for it (checking what changed before undoing), but never explicitly names undo_file_change as the alternative or states when-not to use it. Usage is inferable rather than spelled out.

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