Generate an evidence-led campaign plan with runnable test specs from a buyer profile or existing project. Save the plan and specs without sending any campaign.
Save an evidence-led campaign plan and runnable test specs from a profile or existing project. No campaign is sent.
| Name | Required | Description | Default |
|---|---|---|---|
| out | No | ||
| goal | Yes | ||
| budget | Yes | ||
| profile | No | ||
| project | No | ||
| channels | No | ||
| research | No | ||
| profile_file | No | ||
| research_file | No |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose one important trait — no campaign is actually sent — but omits whether the saved plan persists where, whether it overwrites, permission needs, or what is returned. For a write-style tool with nine parameters, the disclosure is thin but not misleading.
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?
Two tight sentences with the purpose front-loaded and the safety disclaimer second. Nothing is wasted, though the compactness comes at the cost of the parameter detail a tool this complex needs.
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?
A nine-parameter tool with nested objects, no annotations, and no output schema needs substantially more description. Key elements — budget shape, profile vs profile_file vs project precedence, channels, out, and return behavior — are all unexplained.
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% across nine parameters, including nested objects (budget, profile, research) and required goal/budget. The description only loosely gestures at profile, profile_file, project, and research via 'from a profile or existing project'; it does not explain the structure of budget, channels, out, or the file-vs-object alternatives.
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 states a specific verb and resource ('Save an evidence-led campaign plan and runnable test specs') and identifies the input modes ('from a profile or existing project'). It is clear enough to distinguish from siblings like research or pitch, though the term 'evidence-led' is loosely defined.
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?
'No campaign is sent' usefully scopes what this tool does not do, and 'from a profile or existing project' hints at two entry paths. However, it never states when to choose campaign_plan over siblings such as pitch, research, or study, leaving selection to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.