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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, and the description adds real context beyond them: the action is public and irreversible-per-version, each publish creates an immutable version, and the draft is consumed so further edits require a new save. The human-approval requirement and turn-boundary rule are behavioral facts the annotations cannot express.

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 outcome and URL, then the prerequisite, then the approval rule, then versioning. Dense and mostly waste-free, though the mixture of capability description and imperative agent instructions makes it longer than strictly necessary.

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?

For a two-parameter, non-idempotent, destructive publish with no output schema, everything an agent needs is present: prerequisite, approval sequencing, public-visibility consequence, draft consumption, and how to manage the resulting versions.

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 both parameters are already documented. The description still adds meaning the schema does not: content is not passed as a parameter at all, pageId derives from save_draft, and changelog feeds version history and the optimize loop — clarifying the implicit draft-as-input contract.

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 effect: makes the page live at a concrete URL by promoting the current draft. It also distinguishes itself from save_draft by declaring it takes no HTML and consumes whatever the draft holds, so an agent can tell it apart from the sibling write tools without opening either 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 explicit ordering (save_draft first), an explicit prohibition (never in the same turn as save_draft), and an explicit approval gate (show preview URL, wait for a later message). It even pre-empts the ambiguous case where the user says 'publish it' up front, and points to list_versions/rollback for version management.

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