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

Annotations cover the mutation/safety profile (readOnly=false, destructive=false, idempotent=false), and the description adds genuinely new context: the returned preview_url is anonymously readable by anyone with the link and expires in 30 minutes, plus preview_expires_at. That security-relevant disclosure is exactly what annotations cannot convey.

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?

Four short sentences, front-loaded with the core action, then the authoring choice, then the non-publishing guarantee, then the return values. No redundancy and every sentence carries distinct 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 responsibly documents the return payload (preview_url, preview_expires_at) and its lifetime, and covers the main authoring mode choice. Minor gaps remain around the idempotency_key and publish-consent behavior, but the core call-and-interpret loop is covered.

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 low (33%) over a nested schema, but the schema itself carries strong inline descriptions for html, slug, publish, elements, featured_image_url and idempotency_key. The description only adds the html-vs-elements mutual-exclusion hint; it says nothing about kind, idempotency_key usage, or publish consent, leaving compensation incomplete.

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 precise verb+resource ('Create a post or page draft') and immediately clarifies the draft-vs-publish distinction, which separates it from siblings like publish_content and update_content without requiring the agent to open 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 actionable guidance on when to use html versus ordered native elements, and states that creating a draft does not publish it. It stops short of explicitly naming alternatives (publish_content, update_content) or listing exclusions, so it is clear context rather than full when/when-not routing.

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