send_whatsapp_text[demo: deshabilitada] Sends a plain-text WhatsApp message to a customer phone number. Only valid inside the 24-hour customer-service window (Meta error 131026 outside).
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Recipient phone number (local AR or E.164). | |
| text | Yes | Message text body. | |
| mediaUrl | No | Optional public URL of a media file to attach. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds valuable behavioral context beyond the annotations: the 24-hour window restriction and the specific Meta error code. It also notes the demo is disabled ('[demo: deshabilitada]'). No contradiction with annotations; it complements them with operational limits.
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 a single sentence and very concise, but the leading '[demo: deshabilitada]' tag adds minor noise and does not directly serve a functional purpose. Still, the core message is front-loaded and efficient.
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?
For a relatively simple tool with a fully documented schema and meaningful annotations, the description provides the critical operational constraint (24-hour window) and error code. It does not explain return values, but no output schema exists, so that is not required. The 'plain-text' wording could slightly conflict with the optional mediaUrl, but overall the context is sufficient.
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?
The schema provides 100% coverage with descriptions for all three parameters, so the baseline is 3. The description does not add any parameter-level detail beyond the schema, such as formatting for 'to' or the optional nature of mediaUrl.
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 sends a plain-text WhatsApp message to a customer phone number, using a specific verb and resource. The qualifier 'plain-text' distinguishes it from the sibling send_whatsapp_template, making the purpose unambiguous.
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?
It explicitly states the tool is only valid inside the 24-hour customer-service window and mentions the Meta error 131026 outside, providing clear when/not-when context. However, it does not explicitly name alternatives like send_whatsapp_template, though the 'plain-text' distinction implies it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools have overlapping purposes, such as caja_registrar_movimiento vs register_movement, get_payment_intent_status vs open_cobro_status, and adjust_stock vs stock_load. The distinctions are not immediately clear from names/descriptions, causing a high risk of misselection.
Naming is inconsistent: mixes English and Spanish (caja_*, emit_invoice, send_whatsapp_*), and uses different patterns (open_*, get_*, query_*, list_*, etc.). Some names like stock_load and bulk_price_update don't follow a clear verb_noun convention.
50 tools is excessive for most contexts, even for a broad ERP-like domain. Many are UI widgets (open_*) that add clutter and could be consolidated, making the tool set feel heavy and harder to navigate.
The tool set covers many core business functions (products, suppliers, customers, sales, invoicing, shipping, cash register, payments, integrations). However, there are noticeable gaps: purchase requests have only create (no list/update/delete), shipments cannot be updated/cancelled, and sales lack direct update/query by ID.