process_supplier_invoice_image

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly states that the tool creates a Cosmo OCR Invoice and proposes a Purchase Invoice, which are significant side effects. It also implies a data transformation step (from image analysis to structured data). However, it does not mention potential reversibility, error handling, or whether it modifies existing records, which could be important for a creation tool.

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 but information-dense. It front-loads the purpose, then provides a numbered workflow that is easy to follow. Every sentence adds value, including the when-to-use line. No fluff or repetition. The length is justified by the workflow explanation.

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 (6 parameters, 3 required, no output schema), the description is fairly complete: it explains the workflow, the preconditions (Hermes vision_analyze), and the expected outcomes (Cosmo OCR Invoice, Purchase Invoice). It does not describe the return value or post-creation steps, but for an internal workflow tool, this is a minor gap. The absence of an output schema raises the bar, but the description covers the essential context.

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%, and each parameter has a clear French description (e.g., 'Lignes de produits extraites', 'Montant total de la facture'). The description adds context that these parameters come from Hermes's extraction, but it does not elaborate on specific formats, constraints, or relationships beyond what the schema already provides. Baseline 3 is appropriate since the schema handles parameter semantics.

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 the tool's purpose: recording a supplier invoice extracted from an image by Hermes. It specifies the exact action (enregistrer une facture fournisseur), the resource (facture fournisseur), and the workflow (creating a Cosmo OCR Invoice and proposing a Purchase Invoice). This distinguishes it from sibling tools like create_item_from_image or identify_product_from_image.

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 provides explicit when-to-use guidance: 'Utiliser quand l'utilisateur envoie une photo de facture fournisseur.' It also outlines a three-step workflow, making it clear that this tool is called only after Hermes has analyzed the image with vision_analyze and extracted structured data. This implicitly excludes using it for other invoice types or without prior image analysis.

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