Skip to main content
Glama

Upload files to Odoo via link

aidoo_attach

Generate an ephemeral upload link so files go into Odoo without AI exposure; users open it to attach invoices or documents, then retrieve created IDs.

Instructions

Send files into Odoo WITHOUT the content passing through the AI. Generates an ephemeral single-use upload LINK (30 min) that the user opens to drop the files (invoices to digitize, contracts, justificatifs...). NEVER put base64 or raw file content in tool arguments — always use this link flow. action='request_upload' with named file slots (some may be optional), then give the URL to the user; action='status' to retrieve the created attachment/invoice IDs. Use purpose='invoice' to trigger Odoo's invoice digitization (OCR), or model+res_id to attach to an existing record.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filesNo
modelNo
actionYes
res_idNo
purposeNo
upload_idNo
journal_idNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.4/5.0
Behavior5/5

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

The description reveals behavior beyond the sparse annotations: content does not pass through the AI, the link is ephemeral, single-use, and valid for 30 minutes, and the user must open it to drop files. It also explains what status returns, which is valuable operational context not captured elsewhere.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and informative, with the core constraint front-loaded. It is slightly long and runs multiple instructions together, but every sentence carries necessary information and there is little fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters spend a bare schema and an output schema present, the description covers the main workflow and guardrails well. It omits explicit semantics for upload_id and journal_id, which could leave an agent unsure how to complete the status polling or journal-specific invoice upload.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates well by explaining action values, named file slots, purpose='invoice' for OCR, and model+res_id for attaching to existing records. However, upload_id and journal_id are left unexplained; upload_id in particular seems important for the status action, so the compensation is not complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool sends files into Odoo via an ephemeral upload linkache and gives concrete use cases like invoices, contracts, and justificatifs. It distinguishes the link flow from raw base64 arguments but does not explicitly contrast sibling tools such as aidoo_create or aidoo_document, so sibling differentiation is only implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when and when-not guidance: 'NEVER put base64 or raw file content in tool arguments — always use this link flow.' It also prescribes the exact flow: request_upload first, give the URL to the user, then use status to retrieve IDs, with conditional guidance for purpose='invoice' versus model+res_id.

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