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

With sparse annotations (all hints false), the description carries the burden and does so thoroughly. It discloses billing per row and per context fill, synchronous vs asynchronous execution thresholds, retention modes, and ephemeral deletion timing. This adds substantial behavioral context well beyond the structured annotations, with no contradiction.

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?

The description is dense and front-loaded with the core purpose, and every sentence carries relevant operational detail. It is slightly repetitive in the opening two sentences and could benefit from bullet structuring, but it is not bloated.

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 complex batch tool, the description covers the essentials: input methods, mapping behavior, row limits, async behavior, billing, retention, and cleanup. Since an output schema exists, return-value details are unnecessary. Minor omissions like error handling and exact csv_text formatting keep it just shy of 5.

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?

Given 0% schema description coverage, the description compensates well: it explains csv_url/csv_text as row sources, mapping as {column: field_id} with a default behavior, and retention values/default. It does not explicitly spell out form_id or the raw text format of csv_text, but those are reasonably inferable from context and sibling tools.

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?

The description states a specific verb and resource: 'Fill one copy of a PDF form for every row of a spreadsheet.' It clearly distinguishes itself from single-fill siblings like fill_form by emphasizing per-row batch behavior, and the CSV input methods are named upfront.

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 description clearly conveys the intended use case (filling a form for many spreadsheet rows), and it provides operational guidance such as polling get_batch for batches above 50 rows and letting suggest_mapping run when mapping is omitted. However, it does not explicitly contrast with fill_form or fill_form_from_context, so it stops short of full when-not guidance.

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