Skip to main content
Glama
hermoso-ai

Hermoso

Official

Create a WhatsApp message template

create_whatsapp_template

Create and submit a WhatsApp message template for Meta's review, enabling outbound conversations beyond the 24-hour customer-initiated window.

Instructions

Submit a new WhatsApp message template for Meta’s review. This is the ONLY way a business can start a WhatsApp conversation: outside the 24-hour window that opens when a customer messages first, WhatsApp accepts approved templates and nothing else. CATEGORY IS NOT COSMETIC — MARKETING (anything promotional), UTILITY (a transactional follow-up to something the customer did) or AUTHENTICATION (a one-time passcode) decides both what Meta charges for the conversation and the policy the content is reviewed against, and Meta RE-CATEGORISES a template whose content does not match the claim; the reply reports the category Meta actually assigned, not the one requested. The name is lowercase letters, digits and underscores only. Language is never defaulted: en and en_US are different templates to Meta. Submitting does NOT make it sendable — it comes back PENDING and has to be re-read with list_whatsapp_templates. CAROUSEL TEMPLATES ARE SUPPORTED: add a “CAROUSEL” component whose “cards” array holds 2–10 cards, each card carrying its own HEADER (format IMAGE or VIDEO for a media carousel, PRODUCT for a catalog one), an optional card BODY of at most 160 characters — a different and far shorter limit than the message bubble’s 1024 — and up to 2 buttons. Meta requires every card to carry THE SAME components, and if any card has body text then all of them must. At creation a card is only its “components” array; “card_index” belongs to the send payload, not to this one. A MEDIA HEADER NEEDS AN UPLOADED ASSET: any IMAGE, VIDEO or DOCUMENT header — including every card header in a media carousel — must carry example: { header_handle: [ … ] } holding a handle from Meta’s Resumable Upload API, or Meta refuses the whole template with a bare “Invalid parameter”. Hermoso does not upload template media yet, so it refuses that locally and by name instead. A TEXT header needs no handle, and a PRODUCT card carousel takes its pictures from a connected catalog. 0 credits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYeslowercase letters, digits and underscores only, e.g. "order_shipped" (max 512)
wabaIdNothe WhatsApp Business Account id, from list_whatsapp_accounts. Optional when exactly one account is shared with this brand; required when several are, and refused by name for one that is not shared
categoryYesMARKETING = promotional, UTILITY = transactional follow-up, AUTHENTICATION = one-time passcode. It sets the price and the review policy.
languageYesthe language code, e.g. en_US, es_MX, pt_BR — Meta treats each as its own template
componentsYesMeta’s component array. A BODY is the only REQUIRED one: [{ type: "BODY", text: "Your order {{1}} has shipped." }]. Optional HEADER (text max 60), FOOTER (max 60) and BUTTONS (up to 10 in total). Body text max 1024. A carousel is { type: “CAROUSEL”, cards: [{ components: [{ type: “HEADER”, format: “IMAGE” }, { type: “BODY”, text: … }] }, …] } — 2–10 cards, all with the same components, card body max 160, up to 2 buttons each.
parameterFormatNoPOSITIONAL (default, {{1}}) or NAMED
Behavior5/5

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

Annotations only mark readOnlyHint=false, openWorldHint=true, idempotentHint=false. The description discloses far more: Meta re-categorises mismatched templates, the reply reports the actual assigned category, submission results in PENDING status, carousel card constraints (same components, body limit), media header requirement, and local refusal by Hermoso. This goes well beyond annotations and gives the agent realistic expectations.

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

Conciseness3/5

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

The description is a dense wall of text with many sentences, and while each adds value, it is not concise. It front-loads the core purpose and then cascades into detailed edge cases (carousel, media, category). It could be broken into short bullet-like sections for readability, but given the complexity, a 3 is fair — it is adequate but lacks structural concision.

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

Completeness5/5

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

For a creation tool with no output schema, the description covers the post-submission state (PENDING, re-read), the category assignment behavior, media requirements, carousel nuances, and local refusal. It even mentions credit cost (0 credits). The only minor omission is a full response structure, but the description explains the key outcome and next step, making it complete for agent invocation.

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

Parameters5/5

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

Schema coverage is 100%, so baseline is 3, but the description adds substantial semantics beyond the schema. It explains the category's pricing and policy impact, that en and en_US are distinct templates, the name format, carousel component structure, card body limit, and media handle requirement. This enriches parameter meaning significantly beyond the raw schema descriptions.

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

Purpose5/5

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

The description opens with a clear verb-resource pair: 'Submit a new WhatsApp message template for Meta's review.' It further grounds the purpose by stating this is the ONLY way a business can start a WhatsApp conversation outside the 24-hour window, which distinguishes it from sending messages and listing templates. The sibling tools like send_whatsapp_message and list_whatsapp_templates are implicitly separated by this explicit scope.

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 gives explicit when-to-use context: it is the only path to initiate conversations, and it warns that submission does not make the template sendable — it returns PENDING and must be re-read with list_whatsapp_templates. It also specifies constraints like media headers requiring an uploaded asset and Hermoso refusing locally, so the agent knows when the tool will fail and how to avoid it.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hermoso-ai/hermoso'

If you have feedback or need assistance with the MCP directory API, please join our Discord server