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

Annotations only declare readOnlyHint and openWorldHint; the description goes well beyond by disclosing the return payload (embedded base64 PDF resource, page count, remaining quota), the 402 payment-required behaviour, and an explicit cost model (1 document from the monthly plan, or 1 prepaid credit after the cap). That is exactly the quota/rate-limit context annotations cannot carry.

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?

A single dense paragraph with the use case front-loaded and no filler sentences; each clause carries information (templates, params, output, cost). The heavy parenthetical nesting makes it harder to scan than it could be, but nothing is wasted.

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 correctly covers the return shape, and it covers cost, auth, and both template variants. Remaining gaps are minor: nested data field details and auth specifics are delegated to an external URL and to the html_to_pdf sibling rather than stated here.

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 only 33%, but the description compensates by enumerating what each template's data object expects (invoice: seller, buyer, items, tax_rate, currency; itinerary: trip, days) and by naming the filename parameter. It still defers full field shapes to an external URL and doesn't mark which nested fields are optional, so it stops short of fully closing the gap.

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 (render a built-in template) and names the two concrete templates available (invoice, itinerary) plus the output format (clean PDF). It implicitly distinguishes itself from the sibling html_to_pdf by framing the value as 'without writing HTML', so an agent can tell which tool applies.

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?

The opening clause gives a clear when-to-use condition: structured data for an invoice or itinerary where a PDF is wanted without authoring HTML. It references html_to_pdf for shared auth behaviour but never explicitly says 'use html_to_pdf instead when you need custom HTML/layout', so the routing rule is implied rather than stated.

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