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

Goes well beyond the read-only annotations: it discloses field-level redaction shown as "[REDACTED]", capability-based visibility limits, a hard failure mode for mismatched objects, and — critically — that a "live_state": "unreadable" response produces an empty diff that must NOT be read as "nothing changed". That last point prevents a serious misinterpretation an agent could not infer from annotations.

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 action and the id_b-omitted fallback are correctly front-loaded, but the body is a single dense run-on covering permissions, redaction, live-state failure, and explanations. It is also visibly defective: the "explanations" sentence is truncated mid-word ("previous bod…") and the trailing "Through Royally: its server marks it read-only" fragment reads as an artifact rather than intentional content.

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 still conveys the return shape (per-field before/after, diff, live_state, note, explanations) and the error path. For a read-only diff tool with three parameters, an agent has everything needed to call it and to interpret edge-case responses.

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 id_a/id_b/site_id are already documented; the description still adds value by explaining the cross-parameter constraint (both ids must target the same object) and the full consequence of omitting id_b, including the unreadable outcome. It does not clarify ordering assumptions beyond "older"/"newer", which the schema already carries.

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 ("Diff two change-history entries") plus the alternate mode (one entry against live state when id_b is omitted). That distinguishes it from sibling readers like wp_history_get and wp_history_list, which return entries rather than comparisons.

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 operating conditions: both entries must share object_type and object_id or the call errors, non-admin callers can only diff their own entries, and omitting id_b switches to live comparison. It never explicitly routes the agent to wp_history_list to obtain ids or to wp_history_get for a single entry, so alternative selection is left implicit.

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