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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds traits they cannot: the return shape, staleness detection ('flags fields that were changed again since, which undo would refuse'), and the expiry failure mode (status 'expired' after 7 days). That is exactly the kind of edge-case disclosure annotations don't carry.

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?

The most decision-relevant content (what it returns, staleness flag, accepted identifiers, expiry) is front-loaded in three tight sentences. The trailing '(site: demo.royalplugins.com) Through Royally: read-only, runs straight away.' is boilerplate that partially duplicates the readOnlyHint annotation.

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 full burden of explaining return values, and it does: field-by-field before/written/now plus diffs for the specific payload types. The expiry and re-change flags round out the edge cases an agent needs before calling or interpreting 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 coverage is 100% and both parameters are already documented, including the change_id/undo-token duality. The description restates that duality and names the source tool, which adds little beyond the schema. Baseline 3 is appropriate.

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 ('Show one change field by field') and enumerates the exact payload: before value, written value, current value, plus line diffs for post content, CSS and page-builder data. This is clearly distinguishable from the list-level sibling mcp_list_recent_changes.

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?

It tells the agent where the input comes from ('a change_id from mcp_list_recent_changes, or the undo token from the original tool response') and what happens at the 7-day boundary. It stops short of naming the alternative for acting on a change (mcp_undo_last_operation), so the when-to-use-vs-sibling routing is implied rather than stated.

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