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

Annotations only cover the read-only/idempotency profile; the description adds substantial behavior: expiry defaults, noindex emission, real head/footer rendering, CSS/Elementor kit loading, and graded connector-version requirements with failure symptoms and remediation.

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 purpose and the render_screenshot handoff, then layers caveats. Dense with parenthetical version details, but each clause (expiry, noindex, CSS failure mode) carries actionable information.

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 it gets back (preview_url, and share_url when share=true), how long it lasts, and what the rendered result will look like — nothing essential is missing for correct invocation.

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 ttl and share are already documented in the schema. The description's 'default 10 min' and share-for-humans framing mostly restate what the schema says, 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 and resource ('Get a short-lived tokenized PREVIEW URL for a page') and immediately adds the scope differentiator 'WORKS FOR DRAFTS', which distinguishes it from published-page reads like wp_get_page.

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?

Explicitly states when to use it ('to see or screenshot unpublished work before publishing') and routes to the sibling: 'mint the link, then pass preview_url to render_screenshot'. It even gives a when-not/mitigation path for old connectors.

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