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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, but the description adds materially more: the return is a hosted download_url and never the raw bytes, the call consumes one plan generation (pointing to apitemplate_get_account), and repeats are counted. This is exactly the non-obvious behavior an agent needs before invoking a billed write.

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?

Three front-loaded, labeled sentences (WRITE, COST, endpoint) with no filler; the operation, cost model, and API path each earn their place. Nothing is restated from the schema or annotations.

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?

No output schema exists, so the description correctly fills that gap by naming the return (hosted download_url, not bytes). Combined with cost, retry, and endpoint disclosure for a tool with a deep nested settings object, an agent has everything needed to call it correctly and safely.

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 the baseline is 3, but the description adds a meaningful semantic link: Jinja2 placeholders in 'body' such as {{lang}} are resolved from 'data', clarifying how two separate parameters interoperate. It doesn't add detail on the settings/expiration knobs, which the schema already covers.

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 ('renders one PDF') and resource ('from Markdown'), with the 'from Markdown' scope inherently distinguishing it from the sibling create_pdf_from_html and create_pdf_from_url. It also names the mechanism (Jinja2 placeholders) so an agent knows exactly what input style is expected.

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 clear operational context: it's a WRITE, it costs 1 generation of quota, and it should not be retried or repeated unless needed. It does not explicitly route the agent to alternatives (e.g. use create_pdf_from_html for HTML), so sibling selection is left to the name rather than spelled out.

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