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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true. The description adds genuinely new context beyond that: changes take ~1–3 minutes, all edits apply atomically as one new version, and undo is available via restore_version. It omits permission/auth prerequisites and failure/partial-apply behavior.

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-loads the action and the preferred edit path, and every clause carries information (modes, latency, atomicity, undo, required note). Slightly dense in a single run-on sentence, but 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 an output schema present, return values need no explanation, and the description covers mode selection, timing, atomicity, and undo. It would be fully complete with a note on required permissions and what happens when an edit fails to match, but nothing essential to a correct call is missing.

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 description coverage is 100%, so the schema already documents all six parameters including the nested edit fields. The description reinforces 'note is required: what you changed and why' and maps the top-level modes to parameters, but adds little beyond what the schema already states, so the baseline 3 applies.

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 (changes) and resource (an existing site's pages) and enumerates the exact mutation modes it supports: find/replace edits, whole files, deletions, form email. This clearly distinguishes it from siblings like create_site, preview_site, and restore_version.

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 a real preference signal — small find/replace edits are '(preferred)' over whole-file replacement — and routes undo behavior to restore_version. It does not, however, state when to use this tool versus preview_site or create_site, so the exclusions are left implicit.

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