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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes well beyond by disclosing exactly what is overwritten versus preserved, that keep_previous=true stashes the old version as a draft named 'Previous version', that the swap is a single undoable version-history entry, and that a `warnings` list of dropped images / broken links is returned. The reversibility detail is what makes destructiveHint=false credible.

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 core swap and its invariants before preconditions and undo mechanics, and every clause carries information. It is dense but long — the restore_version `file_slug` aside is a slight detour that could be trimmed without loss.

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 tells the agent what comes back (`warnings` and what to do with it) and that the change is not live until publish_site. For a 6-parameter, non-idempotent mutation this covers everything needed to call it correctly.

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 the baseline is 3; the description earns a step up by framing keep_previous as a workflow decision ('putting it back is one more promote') rather than restating the schema, and by noting the page is 'the page' the draft belongs to (page_slug is derivable). It stops short of adding new syntax or format detail beyond the schema.

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 ('Make a draft the page') and immediately disambiguates against its siblings: it replaces layout and text in place, while address, name, SEO, menu entry and links stay. An agent can tell this apart from create_page_draft, rename_page_draft, update_page_seo and restore_version without opening a 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?

Gives an explicit precondition ('Call this ONLY once the user has approved the draft') plus named alternatives with their conditions: restore_version to undo, publish_site to ship it to visitors. When-to-use, when-to-undo and the downstream step are all spelled out.

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