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

Goes well beyond the readOnly/non-destructive annotations: it discloses that nothing is stored, that previews consume a shared hourly plan budget (a real rate limit), the exact return shape (JPEG pictures of up to 4 pages plus a text block with page count and defects), and how problems are surfaced with path and page. The rendering conventions for a missing field (‹path›) and a non-drawing graphic (empty frame) are details an agent could not get elsewhere.

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-loads the purpose, then behavior, then the workflow, and each sentence carries information. The sentences are densely packed with clauses (budget sharing, defect list, placeholder conventions) but none is filler, so the density is justified rather than wasteful.

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?

There is no output schema and the tool has six parameters including nested objects, so the description must carry the return-value burden itself; it does so by naming the image format, page cap, and the accompanying diagnostics block. Combined with the cost warning and the suggested iterate-with-update_template loop, an agent can invoke and use the result correctly without further context.

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 schema already documents csv, data, dpi, template, first_page, and page_count thoroughly. The description adds only the practical hint to request later pages with first_page, restating page-count limits that the schema already enforces, so it does not meaningfully extend parameter meaning.

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 action and resource: it produces pictures of a saved template's pages filled with data, purely for checking appearance before render_template. It explicitly distinguishes itself from the sibling render_template, which is the key confusion risk in this tool family.

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 a concrete workflow (preview, look at the pictures, change the body with update_template, preview again) and places itself before render_template. It stops short of stating when a preview can be skipped, e.g. for pure data validation where no visual check is needed, so it is clear but not exhaustive.

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