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

With annotations only covering safety flags, the description adds real behavioral context: it never publishes, it can surface validation warnings, screenshots may be unavailable/truncated and are retryable without recreating the draft, and the result image must be embedded in the final answer. The 'readOnlyHint: false' flag combined with 'idempotent: true' is consistent with an artifact-producing preview rather than a state mutation, so nothing is contradicted.

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?

Dense but front-loaded: the trigger condition, prerequisite lookup and return shape come before the presentation rules. Multiple sentences are justified because each carries a distinct instruction (lookup source, output format, truncation handling, non-publishing guarantee).

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 workflow tool that returns rich artifacts, the description covers the lookup path, the return shape, validation output and how the agent must present the image and link. Some of this duplicates what an output schema would carry, but the agent-facing presentation instructions are not captureable elsewhere, making the definition operationally complete.

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?

Only one parameter exists and the schema gives it 0% description coverage, so the description must carry the load. It does tell the agent where draftId comes from (search_post_drafts), which is genuinely useful, but adds no format or semantic detail about the identifier itself.

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?

The description establishes a specific verb+resource: previewing a saved Postlyra draft, and enumerates what it returns (documentJson/richHtml, native JPEG, display instructions, validation warnings). It clearly scopes to drafts, which usefully disambiguates from search_posts/get_post despite the 'preview_post' name saying 'post'. It stops short of explicitly naming the sibling it differs from.

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?

It gives a direct when-to-use ('Use this when previewing a saved draft') and a concrete prerequisite workflow: obtain draftId via search_post_drafts first. It also tells the agent to retry unavailable screenshots without recreating the draft. No explicit when-not-to-use (e.g. published vs. draft posts) is stated, so it falls short of a 5.

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