Create a lead scoring rule that awards positive or negative points to contacts matching a defined condition.
Create a lead scoring rule. Awards points to contacts matching a condition.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Rule name (e.g. 'Opened email') | |
| points | Yes | Points to award (positive or negative) | |
| isActive | No | Whether the rule is active (default true) | |
| condition | No | Condition object that determines which contacts match |
Changes observed during successful MCP inspections.
v4.71.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description bears the full burden. It says points are awarded to matching contacts, but never states whether existing contacts are re-scored immediately or only on future evaluation — a critical ambiguity given a dedicated conduyt_recalculate_scores sibling exists. No mention of permissions, duplicate/conflicting rule handling, or what the response contains.
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 short sentences, zero filler, with the mutation and its effect front-loaded. Nothing to trim.
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 schema is fully documented and no output schema exists, so parameter-level completeness is fine. However, for an unannotated mutation that changes contact scores, the description omits the retroactivity/response behavior an agent would need to call it confidently.
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 100%, with name, points (positive/negative), isActive default, and condition all documented inline. The description adds no syntax or shape detail for the loosely typed 'condition' object, so baseline 3 is appropriate.
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?
Specific verb + resource ('Create a lead scoring rule') plus a one-line statement of the rule's effect ('Awards points to contacts matching a condition'). Siblings (list/update/delete_scoring_rule, recalculate_scores) make the create intent unambiguous, though the description never explicitly names them.
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 guidance on when to use this versus conduyt_update_scoring_rule or conduyt_recalculate_scores, and no prerequisites (e.g. whether scoring must be enabled, whether rules apply to existing contacts). The agent must infer usage entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.