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

Annotations already declare destructive=true and idempotent=true, but they cannot say what is destroyed; the description adds that valuable scope — the draft is replaced while the live publication is untouched. It does not disclose what happens when the supplied revision is stale (conflict/rejection), which is the main behavioral risk for a destructive overwrite.

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?

Two short sentences, front-loaded with the action and followed by the critical scope constraint — no wasted prose. The second sentence earns its place; the first is slightly compressed to the point of ambiguity ('current revision').

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?

This is a destructive, full-document write with a nested object schema, no output schema, and no explanation of the revision precondition, conflict behavior, retry/idempotency flow, or what the caller gets back (e.g., a new revision number). Given the tool's complexity, the two-sentence description leaves too much for the agent to infer.

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 only 33% — only idempotencyKey is documented in the schema. The description does not explain that `document` is a complete, non-partial replacement (additionalProperties: false, many required fields) nor that `revision` is an optimistic-concurrency token that must match the current draft revision; 'using the current revision' is the only hint and it is vague. An agent could plausibly send a partial document or a stale revision and be surprised.

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?

"Replace the draft using the current revision" names a specific verb (replace) and resource (draft), and the second sentence separates it from publish_site/publication_status by stating it does not affect the live publication. What remains ambiguous is what 'the draft' is scoped to (the whole site document vs. a page) and what 'current revision' means operationally.

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?

The clause "Does not change the live publication" implicitly routes publishing intent to publish_site, which is useful. But there is no explicit statement of when to call save_site versus create_site, preview_site, or publish_site, and no precondition guidance such as needing the latest revision from get_site before saving.

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