facturx_create_pdf

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

With no annotations provided, the description carries the full burden of disclosing behavior. It does disclose the primary side effect: 'Sauvegarde le résultat sur disque' (saves to disk), which is the key mutating action. However, it does not clarify whether an existing output file is overwritten, whether the output directory must exist, or what happens on failure (e.g., invalid XML). These are secondary but useful details for a mutation tool without annotations.

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 efficient: two sentences, no filler, with the main action placed at the start. It conveys the essential behavior and the optional variant without redundancy. It is slightly verbose in phrasing but remains well-structured and readable. A 4 rather than 5 because it could be tightened (e.g., 'peut intégrer le XML dans un PDF existant' could be shortened, though clarity is not compromised).

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?

Given the tool's complexity is low (three parameters, no output schema, no nested objects), the description is sufficiently complete: it names the artifact type, the embedding mechanism, the optional existing-PDF path, and the disk write. Missing details (overwrite, error handling) are minor and would be expected in a summary, but they are not critical for a straightforward file-generation tool. The output format is implied (a PDF), even without an output schema.

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%, as all three parameters have descriptions. The description adds minimal new semantic value over the schema: it clarifies the optional parameter's purpose (embed XML in an existing PDF) and reinforces that the output is a PDF file. Because the schema already defines every parameter, the baseline of 3 applies; the description does not fill a coverage gap.

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 specifies a verb/action ('Crée un PDF'), the resource (a PDF with embedded Factur-X XML), and optional transformation (embed XML in an existing PDF). It distinguishes itself from sibling tools: it creates PDFs, whereas siblings like facturx_parse/extract read them, facturx_generate produces XML, and chorus_* handle submission. No ambiguity remains.

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 states the core use case (create a PDF with embedded Factur-X XML) and mentions the optional integration into an existing PDF, which implicitly communicates when one might choose this variant. However, it gives no explicit guidance on when not to use this tool, nor does it reference alternatives such as facturx_generate or how this tool fits in the generation/validation workflow. Usage is clear but not explicitly contrasted against siblings.

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