What changed in the account

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

Annotations already disclose readOnlyHint=true and openWorldHint=false, so safety and data boundary are covered. The description adds real behavior beyond that: the baseline-selection rule and the 'live items first' ordering. It does not say what happens when no prior snapshot exists, whether output is truncated, or how large a diff can be, which are the notable remaining gaps.

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 that defines the operation first and then the change taxonomy, closed by a short ordering note. Nothing is repeated from the schema or annotations, and no sentence is filler.

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, the description carries the return-value burden and does so by enumerating the change categories, which effectively sketches the result shape. Missing pieces are the empty/no-snapshot case and any indication of result volume or aggregation, which matter for a diff tool but are secondary.

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%, so baseline is 3. The description still earns a bump: it explains that `since` acts as a snapshot-selection anchor rather than a strict filter, meaning the agent learns it can get a diff as-of an arbitrary past date. `platform` and `workspace` are already fully documented in the schema and are not restated, appropriately.

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 exact computation — a diff between the latest snapshot and the prior one (or the newest before `since`) — and enumerates the change categories: added, removed, status, content, audience, structure. That is far more specific than the title alone and distinguishes it from inspection siblings like show_journey or what_breaks, though it never explicitly contrasts itself against 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?

Useful usage detail is embedded in the `since` fallback rule (baseline becomes the newest snapshot before that date), which tells the agent how to steer the comparison. However there is no explicit when-to-use/when-not guidance and no named alternative (e.g. what_breaks for regressions, show_journey for flow-level views), so routing must be inferred from the sibling names.

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