estimate_segment_classify_scope| Name | Required | Description | Default |
|---|---|---|---|
| senders | No | The teammate emails whose people the first run would tag, as you'd pass to classify_segment_group. Omit for everyone. | |
| agent_ids | No | The campaign (agent_tasks) ids the segment would track, from list_classifiable_campaigns — the value you'd pass as `criteria.agent_ids`. Omit for every campaign. |
Changes observed during successful MCP inspections.
Input schema / properties / sendersAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "The teammate emails whose people the first run would tag, as you'd pass to\nclassify_segment_group. Omit for everyone."
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation is reinforced by the explicit statement 'Nothing is created or charged,' and the description adds the important nuance that this is an estimate, not the exact run figure. This goes beyond the annotation by clarifying the no-side-effect scope and the estimate-vs-exact distinction.
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?
The description is compact and front-loaded with the core purpose, followed by usage guidance and the return contract. The phrasing 'Quote the first classify run' is slightly awkward, but every sentence adds value and the returns section is appropriately included given there is no output schema.
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?
The definition covers purpose, when to use it versus the sibling, the no-side-effect guarantee, and the return shape in the returns block. Since there is no output schema, including the returned keys is essential, and this description fills that gap completely for an estimate tool.
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 coverage is 100%, so the schema itself already documents both parameters. The description adds context about campaigns the segment would track, but it does not need to repeat parameter details; the baseline of 3 applies because the schema carries the semantic load.
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: 'Quote the first classify run of a segment group that doesn't exist yet' and clarifies it returns a people count and credit estimate. It also distinguishes itself from classify_segment_group by noting that the sibling returns the exact figure once the group exists.
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 explicit: use it to tell the user the cost before creating the group, and once the group exists use classify_segment_group instead. This names the exact alternative and the condition that selects between them, leaving no ambiguity.
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.