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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation context: the newest-first ordering and the constraint that only the most recent change is reversible, which materially shapes how an agent uses the results.

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?

Two sentences, zero filler. The ordering and returned fields are front-loaded, and the second sentence carries only the actionable undo constraint.

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?

An output schema exists so return values need not be explained, and annotations cover the safety profile. The description supplies the remaining essentials: what the list contains, its ordering, and how it feeds undo_voice_change.

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 100% – limit, writer and workspace are all documented in the schema, including the 'me' selector and the workspace requirement. The description adds no parameter-level detail beyond ordering, so the baseline 3 applies.

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 and resource (list changes to the writer's voice profile) plus the ordering (newest first) and the exact payload fields (what, who, where, when). This clearly distinguishes it from get_voice_profile (current state) and list_voice_examples (materials), both present as siblings.

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?

Gives clear operational context and explicitly routes the follow-up action: only the newest change can be undone, and its id should be passed to undo_voice_change. It does not, however, state when to prefer this audit-log tool over get_voice_profile or how it relates to the voice-editing siblings.

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