What changed since revision N

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds that output mirrors notification _meta, but says nothing about journal retention, truncation when limit caps results, or ordering — gaps that matter for a replay tool.

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 waste, with the core action front-loaded and the audience/use case and return shape following. Nothing repeats the name or title.

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?

No output schema exists, and the description does summarize the return (revisions plus touched keys, matching _meta). With annotations covering safety and full schema coverage, only the limit/truncation and stale-revision behavior remain unstated.

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 100% and both uri and since_revision are documented in the schema itself. The description's "differential" framing reinforces since_revision's semantics but adds no syntax, default, or edge-case detail (e.g. an expired revision) beyond the schema.

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: "Replay the differential change journal for a resource," and clarifies the payload shape. It does not name any sibling (e.g. femboy_recall or femboy_ack_toast) to distinguish itself, but the read-only journal replay purpose is unambiguous.

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?

"for a client that was offline and missed notifications" gives a concrete triggering scenario for when to use this tool. It offers no explicit exclusions or named alternatives, so the agent must infer that live-state reads should go elsewhere.

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