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

Goes well beyond annotations (which only declare readOnly false, destructive false, non-idempotent, open-world). It discloses the 24-hour link expiry, that the editor link keeps template and data editable, and the important state transition where editing on the page turns the result into a plain HTML document requiring update to its html. That is exactly the kind of consequence an agent needs before committing to the call.

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?

One long run-on sentence stitched together with em-dashes and nested parentheticals, including a colon-chained clause about page editing. The purpose is front-loaded, but the middle section about editability is buried where it reads as an aside rather than a key caveat. It could be restructured into two or three short sentences without losing content.

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 six-parameter, nested, open-world tool with an output schema, this covers the purpose, the two input modes, defaults implied by omission, and the main lifecycle caveat. It does not address the case where both template and template_id are supplied, nor any auth or quota expectations, but with an output schema present nothing further is needed about return values.

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, and the description mostly restates it. It does add two pieces of meaning not in the schema: that omitting data falls back to the template's sample, and that template_id values come from list_templates while data must match get_template's sample. Useful cross-references, but no additional syntax or constraint detail.

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+output: "Fills a template with JSON data and prints it to PDF", then enumerates the artifacts (download link, 24h validity, editor edit link). It also distinguishes the two modes (gallery template via template_id vs your own template source), which separates it from render_pdf. The density of parentheticals makes the core statement harder to extract than it should be.

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 real routing guidance: template_id comes from list_templates, the data shape comes from get_template's sample, and the language is covered by read_guide topic "templates". It states the two mutually exclusive input modes and that omitting data prints the sample. It never explicitly contrasts with render_pdf or says when to prefer one over the other.

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