marketing_snapshotAdvertising performance: spend, reach, clicks, cost per lead, per campaign, plus the CRM join. [scope: marketing:read]
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| ok | No | False when the call was refused or failed; see error. | |
| error | No | Machine-readable refusal code (a string), present only when ok is false. | |
| message | No | Human-readable explanation of a refusal (a string). |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "properties": {
+ "error": {
+ "description": "Machine-readable refusal code (a string), present only when ok is false."
+ },
+ "message": {
+ "description": "Human-readable explanation of a refusal (a string)."
+ },
+ "ok": {
+ "description": "False when the call was refused or failed; see error.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the [scope: marketing:read] auth requirement, which tells the agent a permission is needed before calling. It does not state the reporting period or freshness of the snapshot, but nothing contradicts the annotations.
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 lists the metric payload, followed by a bracketed scope tag. No filler, no restatement of the title, and the most important content (what you get) comes first.
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?
With an output schema present, the description needn't explain return values, and with zero params the input side is trivially complete; the annotations cover safety. The only gap is the reporting window or aggregation scope of the snapshot, which an agent must infer.
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 tool takes zero parameters, so per the rubric the baseline is 4. The description correctly implies there is nothing to configure — it is a fixed snapshot — and the empty schema with additionalProperties:false is consistent with that.
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 names the resource (advertising performance) and enumerates the specific metrics returned: spend, reach, clicks, cost per lead, per campaign, plus a CRM join. An agent knows exactly what this returns. It does not, however, distinguish itself from sibling dashboard_snapshot or partner_overview, which sound like competing overview tools.
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?
Usage is only implied: 'advertising performance ... per campaign, plus the CRM join' suggests when the tool is relevant, but there is no when-to-use statement, no exclusion, and no reference to a sibling alternative such as ad_attribution or dashboard_snapshot. The scope tag gives a permission constraint rather than selection guidance.
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.