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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial context: the 7-day retention limit, per-user scoping with the all_users admin exception, that undo tokens are only available while undo is possible, and exactly what each row contains. This is well beyond the annotation surface.

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 the core purpose and scope, then row contents, then the mcp_get_change pointer. Dense and information-rich; the trailing '(site: ...) Through Royally: read-only, runs straight away' is slightly noisy but adds modest signal.

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, so the description's enumeration of row fields (time, tool, target_label, undo_summary, connection, undone flag, undo token) fully compensates. Combined with retention limits and admin scoping, an agent has everything needed to call and interpret it.

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%, so all five parameters are already documented in the schema (limit, tool, all_users, include_undone, site_id). The description only reinforces the all_users admin nuance and the change_id routing, both of which are essentially repeats of structured fields. 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+resource (list changes made through Royal MCP), the exact scope (undo-tracked writes from the last 7 days by the same user), and distinguishes the tool from mcp_get_change for before/after values. An agent can identify this as the audit/undo-history listing tool without opening the schema.

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?

Clearly says this lists still-reviewable changes and routes the agent to mcp_get_change (pass a change_id) when before/after values are needed. It implies the undo-review workflow but doesn't explicitly exclude or compare against mcp_undo_last_operation/undo status siblings.

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