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

Annotations only say readOnly=false, idempotent=false, destructive=false; the description goes well beyond them by explaining that every call appends a version (why it is not idempotent), that plan quotas (Free 10 / Pro 50 / MAX 200 / Enterprise unlimited) cause the oldest version to be permanently deleted with no rollback, and that the live and preview versions are never pruned. This nuance actually reconciles the destructive=false hint rather than contradicting it, since the served page is never destroyed.

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-loaded with purpose and preview semantics, then organized under clear headers (Version history, Workflow, HTML guidelines). It is on the long side and carries some low-value ballast — the Japanese tagline 'ページ内容の保存・更新・デザイン変更。' and the niche form-page workflow — but every other line is actionable.

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 10-parameter mutation tool with nested objects and no output schema, the description covers everything an agent needs: version quota and pruning consequences, why nothing is visible until create_preview, HTML document requirements (doctype, Tailwind CDN, <section> wrapping), and the data-cta tracking requirement for conversion goals. Nothing material is left unstated.

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 schema already documents js, css, sections, patterns, designOverrides, etc.; most of the description's parameter notes (css only for non-Tailwind styles, js Pro+, sections need description ≥20 chars and 0-indexed sequencePosition) repeat the schema verbatim. The only genuine addition is tying 'sections' to the actual <section> tags and the backward-compatibility preference for sections over patterns, which is marginal. Baseline 3 is appropriate.

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?

Opens with a specific verb + resource + object: 'Save a new version of a Convika landing page's HTML.' It also immediately distinguishes itself from siblings by stating that the live page and preview link do not change until create_preview/publish_site are called, so an agent can separate this from create_preview, publish_site, and create_landing_page without opening any 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 ordering (create_site → save_page_content → create_preview), an explicit gate for the risky sibling ('Use publish_site only after explicit user approval to go live'), and a separate branch for form pages (create_landing_page_preview → create_form → save_page_content → create_preview). When-to-use and when-not-to-use are both spelled out.

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