Preview slide (design check only — does NOT save a presentation)

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

With no annotations provided, the description carries the full disclosure burden and does so thoroughly: it discloses the side effect ('saves it to disk'), the return contract ('file path (not the image data)'), the required follow-up action ('Open/view that PNG file with whatever image-reading capability your agent has'), and the hard boundary ('is NOT how a presentation gets delivered'). No behavioral trait an agent needs is left to inference.

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 the scoping tag 'DESIGN-ITERATION TOOL ONLY' and the core mechanism in the first sentence, with each subsequent sentence adding operational guidance. However, the non-deliverable warning is asserted three times ('does NOT produce a .pptx', 'NOT how a presentation gets delivered', 'the only tool that creates a deliverable'), so a few words are redundant without adding new 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?

For a 4-parameter tool with no output schema and no annotations, the description covers every operational fact an agent needs: input form (complete self-contained HTML), output contract (file path, not image data), side effect (PNG written to disk), the agent's next step (view the image), and the workflow handoff to build_pptx. Nothing essential is missing.

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 description coverage is 100%, so the baseline is 3. The description's 'single complete HTML document (with inline CSS)' loosely echoes the schema's documented html parameter but adds no syntax or format details beyond it, and the other three parameters are left entirely to the schema. The description does not compensate further, but with full schema coverage, it doesn't need to.

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 — 'Renders a single complete HTML document to a PNG image and saves it to disk, returning the file path' — and immediately distinguishes itself from the sibling tool: 'does NOT produce a .pptx and is NOT how a presentation gets delivered.' The title's 'design check only' reinforcement makes the scope unmistakable. An agent cannot confuse this with build_pptx 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?

Explicitly scopes when to use it: 'Use it only to check how one slide looks while you're still tweaking its HTML/CSS.' It also gives the when-not condition and the alternative: 'Once the user's slides are finalized, you MUST call build_pptx to actually produce the .pptx file.' This is direct routing guidance with an explicit exclusion, leaving nothing to inference.

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