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

Annotations mark this as a non-readonly, non-destructive, non-idempotent write, and the description adds substantial context beyond them: nothing is written into the PDF, billing (one context fill, first 5 per month free), polling cadence (~20s via get_job), retention semantics including ephemeral deletion at 60-70 minutes, and exactly what dry_run does and does not verify. This is unusually complete behavioral disclosure.

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 purpose and the key distinction in the first clause, and each subsequent sentence carries non-redundant information (billing, retention, dry_run). It is dense and runs as a single block rather than being broken into scannable segments, which slightly hurts fast parsing of a long description.

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?

An output schema exists, and the description still orients the agent on what comes back (job_id, proposal_id) and how to poll. Combined with billing, retention, and dry_run coverage, an agent has everything needed to call this correctly, including cost and side-effect expectations.

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 0% across 9 parameters, so the description carries the burden and largely meets it: it enumerates policy values (safe writes high+medium confidence, strict high only), retention values (ephemeral vs account_default, with the rule that it only applies when this call creates the form), dry_run semantics, and the input identifiers (form_id/library vs pdf_url/pdf_base64, context_text/context_urls). It stops short of individually defining context_urls or the base64 format, so not quite a 5.

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 ('Prepare a form from documents') and immediately defines the distinguishing behavior: it produces a proposal of every answer with its source, gaps, and disagreements rather than writing. Contrasts explicitly with the sibling fill_form_from_context, so an agent can differentiate without opening either schema.

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 an explicit workflow ('read the proposal, answer what is missing, then commit') and names the sibling that writes directly (fill_form_from_context) versus this one that doesn't. Also explains dry_run as a rehearsal path and how to use it before committing.

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