document_generate

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world; the description adds genuinely new behavior: dual PDF+HTML output, the base64-vs-local-file dichotomy, and the no-storage/public nature. It stops short of covering failure modes (invalid field sets, missing required keys, what happens if outFile path is unwritable).

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-loaded with the purpose and output modes, then the field spec. Every element earns its place, but the dense parenthetical field grammar is hard to scan and would benefit from flatter structuring; it is long because it is information-dense, not padded.

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 nested objects, no output schema, and an opaque `fields` parameter, the description carries the full burden and does: document types, required vs optional fields, date format, output transport, and the natural next step (signing). No output schema means the return-value explanation it provides is essential and present.

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?

This is the tool's key strength: the `fields` object is opaque in the schema (additionalProperties), and the description supplies the full per-type schema including nested locator/locatar/contract/garantie objects and which subfields are optional. It also explains the outFile/response tradeoff and the date format dd.mm.yyyy, which the schema does not.

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 (generate) and resource (legal document), names the two supported document types and enumerates their required field shapes, so an agent knows exactly what will be produced. This is far beyond a restatement of the name and clearly distinguishes it from sibling builders like declaration_build or dosare_document by document type.

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 concrete operational guidance: pass outFile to persist the PDF and then sign with agent_sign_pdf, or omit it to receive base64, plus 'Public, nothing stored.' It does not explicitly say when to prefer this over the sibling declaration_* or proforma/document PDF tools, so routing among similar generators is left partly to inference.

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