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

The description adds meaningful behavioral context beyond annotations: it discloses billing cost ('Billed as one context fill'), which is a non-obvious side effect, and clarifies that only the CSV header row is considered. The idempotentHint and destructiveHint annotations are not contradicted, and the description does not over-promise write or read behavior.

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 concise and front-loaded with the core purpose. Each sentence adds useful information: purpose, input behavior, and billing. There is slight redundancy between 'Propose which spreadsheet columns fill which PDF form fields' and 'proposes which column fills which field,' but overall it is well-structured and efficient.

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?

The description captures the essential invocation context: what input is needed, which CSV parameter forms are accepted, what portion of the CSV is used, and the billing cost. Since an output schema exists, not describing return shape is acceptable. The main remaining gap is dependency on the schema title for understanding form_id.

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?

With 0% schema description coverage, the description must compensate for parameter meaning. It explicitly identifies csv_text and csv_url as CSV input alternatives and adds that only the header row matters Bolt. However, it does not describe form_id at all, nor does it clarify that one CSV source must be provided despite both being optional in the schema.

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 clearly states that the tool proposes a mapping from spreadsheet columns to PDF form fields, which is a specific verb and resource. It distinguishes conceptually from fill/compose siblings by emphasizing 'propose' rather than executing a fill, though it does not explicitly name any sibling tool.

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 gives clear context: it is used when you have a CSV (csv_text or csv_url) and a form_id, and the goal is to get a proposed mapping. It also narrows input expectations with 'Only the header row matters.' However, it does not explicitly state when not to use it or mention alternatives such as fill_form or fill_batch.

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