List recent Google AdsAgent task history using opaque task references.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| connection_context | No |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | No | ||
| code | No | ||
| error | No | ||
| needs | No | ||
| tasks | No | ||
| reason | No | ||
| retryable | No | ||
| error_code | No | ||
| next_action | No | ||
| support_ref | No | ||
| invalid_fields | No | ||
| rejected_paths | No | ||
| origin_support_ref | No |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "properties": {
+ "code": {
+ "type": "string"
+ },
+ "error": {
+ "anyOf": [
+ {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "additionalProperties": true,
+ "properties": {
+ "code": {
+ "type": "string"
+ },
+ "details": {
+ "additionalProperties": true,
+ "properties": {},
+ "type": "object"
+ },
+ "message": {
+ "type": "string"
+ },
+ "retryable": {
+ "type": "boolean"
+ },
+ "support_ref": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ }
+ ]
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "error_code": {
+ "type": "string"
+ },
+ "invalid_fields": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "needs": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "next_action": {
+ "anyOf": [
+ {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "additionalProperties": true,
+ "properties": {},
+ "type": "object"
+ }
+ ]
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "ok": {
+ "type": "boolean"
+ },
+ "origin_support_ref": {
+ "type": "string"
+ },
+ "reason": {
+ "type": "string"
+ },
+ "rejected_paths": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "retryable": {
+ "type": "boolean"
+ },
+ "support_ref": {
+ "type": "string"
+ },
+ "tasks": {
+ "items": {
+ "additionalProperties": true,
+ "properties": {
+ "completed_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "created_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "result_summary": {
+ "anyOf": [
+ {
+ "additionalProperties": true,
+ "properties": {},
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "started_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "status": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "task_ref": {
+ "type": "string"
+ },
+ "task_type": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+}Input schema / properties / connection_contextAdded value: +{
+ "pattern": "^mctx_v1_[0-9a-f]{64}$",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only and non-destructive safety, so the bar is lower. The description adds the 'recent' ordering/windowing implication, but it does not say how far back 'recent' goes, whether results are paginated, or how the limit interacts with the window.
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?
A single front-loaded sentence keeps it tight, but the clause 'using opaque task references' is both wasted space and misleading given the actual schema. Precision matters more than brevity here and the clause detracts.
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?
An output schema exists so return values need not be described, but with 0% schema coverage on two parameters and no mention of how 'recent' is scoped, an agent cannot call this confidently. The description leaves the practical paging and context-passing behavior undefined.
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 0% for both parameters, so the description must compensate and does not. It only alludes to 'opaque task references', which is not even a parameter; limit (1-100, default 20) and the connection_context pattern go entirely unexplained.
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?
States a specific verb and resource: list recent Google AdsAgent task history, which is distinguishable from google_ads_task_get by the plural 'list' and 'history' framing. The trailing phrase 'using opaque task references' muddies the picture because no such parameter exists in the schema.
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?
There is no explicit guidance on when to use this versus google_ads_task_get or tasks_get_status; the agent must infer that this is the enumeration counterpart to a single-task fetch. 'Recent' hints at a time window but never defines it or states a fallback for getting older tasks.
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.