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 reinforces read-only while adding substantive behavior: the implicit draft-vs-live baseline, what `since: 'previous'` widens to, and that `include_versions` returns three snapshots. It stops short of describing output shape or any size/latency limits, which keeps it from a 5.

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?

Every sentence carries information: the first defines the output scope, the second the default comparison, the third and fourth the alternate modes, and the last the safety hint. It is front-loaded with the core behavior and has no 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 usefully sketches the return categories (added/removed/changed pages, theme/header-footer changes, optional snapshots). It does not mention result size, pagination, or how large diffs are reported, which is a modest remaining gap for a five-parameter comparison tool.

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 80%, so the baseline is 3, but the description adds real meaning: it explains that `from` + `to` compares any two of live/draft/previous and gives the concrete example of 'previous' to 'live' being what the last publish did. `site_id` is left unexplained, which is the only gap.

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 opens with a specific verb ('Summarise what changed') and enumerates exactly what is captured: pages added/removed, content changes, and theme or shared header/footer changes. No sibling tool performs a diff/snapshot comparison, and this scope statement makes that distinct role unmistakable.

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 clearly explains the default comparison ('draft against what is live — what is waiting to be published') and when to switch modes via `since: 'previous'` or `from` + `to`. There is no explicit exclusion or named alternative tool, but the mode-selection guidance effectively tells an agent which configuration to pick for which question.

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