Skip to main content
Glama
logly

mureo

by logly
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

meta_ads_conversions_send_purchase

Send a purchase event to Meta's Conversions API for accurate attribution. Provide amount, currency, and hashed user identifiers; returns Meta's events_received acknowledgement. Ideal for tracking sales from server-side data.

Instructions

Sends a single Purchase event via the Meta Conversions API — the most common CAPI use case. Returns Meta's events_received acknowledgement. Mutating on Meta's side. Required fields model a typical purchase: amount, currency, and hashed user identifiers. For other event types use meta_ads_conversions_send_lead (leads) or the generic meta_ads_conversions_send (AddToCart / custom events / batching multiple events).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
valueYesPurchase amount in the specified currency. Decimal for currencies with minor units (USD 9.99); integer is fine for JPY.
reasonNoWhy this change is being made: one or two sentences naming the evidence and the expected effect. Stored in the journal and on the action_log entry this call produces, for the operator and the next session.
currencyYesISO 4217 currency code (USD, JPY, EUR, GBP). Must match the ad account's reporting currency or be one that Meta can convert.
pixel_idYesMeta Pixel ID the event is attributed to. Find via meta_ads_pixels_list. CAPI events flow into the same pixel as browser events; dedupe happens on event_id if one is supplied in user_data / custom_data.
user_dataYesUser identifying fields for attribution. Supported keys: em (email), ph (phone), fn (first_name), ln (last_name), zp (zip), ct (city), st (state), country, external_id, client_ip_address, client_user_agent, fbc (click ID), fbp (browser ID). mureo hashes em / ph / fn / ln / zp / ct / st / country / external_id with SHA-256 before sending — pass raw PII; do not pre-hash.
account_idNoMeta Ads account ID in the format 'act_XXXXXXXXXX' (e.g. 'act_1234567890'). Optional — falls back to META_ADS_ACCOUNT_ID from the configured credentials. The leading 'act_' prefix is required.
event_timeYesUNIX timestamp (seconds) of the purchase. Must be within the last 7 days.
content_idsNoProduct IDs associated with the purchase — catalog retailer_ids for DPA attribution. Optional but recommended when a catalog is in use.
test_event_codeNoMeta Events Manager test_event_code. When set, the event is routed to the test event stream visible in Events Manager instead of production reporting. Use for validation; drop the field once verified. Get the code from Events Manager → Test Events tab.
event_source_urlNoFully-qualified URL where the event occurred. Required by Meta for action_source='website' events; recommended for any browser-triggered CAPI event to improve attribution match rate.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.20.0
    • addedInput schema / properties / reason
      Added value: +{
+  "description": "Why this change is being made: one or two sentences naming the evidence and the expected effect. Stored in the journal and on the action_log entry this call produces, for the operator and the next session.",
+  "maxLength": 500,
+  "type": "string"
+}
  2. Changed1 schema field changedv0.10.37
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed1 schema field changedv1.0.7
    • changedInput schema / required
      Previous value: -[
-  "account_id",
-  "pixel_id",
-  "event_time",
-  "user_data",
-  "currency",
-  "value"
-]New value: +[
+  "pixel_id",
+  "event_time",
+  "user_data",
+  "currency",
+  "value"
+]
  4. Addedv0.9.12
  5. Removedv0.9.6
  6. Addedv0.9.2
  7. Removedv0.9.1
  8. Addedv1.0.5

TDQS

A4.8/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It states 'Mutating on Meta's side' which gives a behavioral hint, and mentions the return value 'Meta's events_received acknowledgement', which is useful. However, it doesn't disclose potential side effects like idempotency, deduplication behavior (though mentioned in pixel_id schema), or rate limits. The description also doesn't mention authentication requirements or whether the event is irreversible, but given the tool's simplicity, a 4 is justified as it covers the key behavioral points.

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

Conciseness5/5

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

The description is concise, two sentences in the main body, with the first sentence stating the core purpose and the second routing to siblings. It's front-loaded with the essential purpose, then provides necessary context without fluff. Every sentence contributes to clarity, and the structure is efficient for an agent to parse quickly.

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?

Given the tool's complexity (10 parameters, 5 required, nested user_data object), the description is surprisingly complete. It covers the purpose, usage, key behavioral notes (hashing, dedupe), and alternatives. The absence of output schema is mitigated by the description stating return is 'Meta's events_received acknowledgement'. The rich parameter schemas cover the rest, so nothing critical is missing for an agent to call this correctly.

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 description coverage is 100% (all parameters have descriptions), so baseline is 3. However, the description adds significant value beyond the schema by explaining required fields model a typical purchase and clarifying user_data hashing behavior ('mureo hashes em / ph / fn / ln / zp / ct / st / country / external_id with SHA-256 before sending — pass raw PII; do not pre-hash'). It also explains dedupe on event_id and currency conversion, which are not in the schema. This goes well beyond what the schema provides.

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 states a specific verb ('Sends a single Purchase event'), a specific resource ('Meta Conversions API'), and clearly identifies this as the most common CAPI use case. It distinguishes itself from sibling tools by naming meta_ads_conversions_send_lead for leads and the generic meta_ads_conversions_send for other events like AddToCart or batching, making it clear when to use this tool versus alternatives.

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 explicitly says 'For other event types use meta_ads_conversions_send_lead (leads) or the generic meta_ads_conversions_send (AddToCart / custom events / batching multiple events).' This provides clear when-to-use and when-not-to-use guidance, directly telling the agent which sibling to choose for different scenarios. It also mentions the typical fields for a purchase, setting expectations for the required parameters.

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

Deploy Server

Other Tools