AI analysis of a contact list — breakdown by industry, title, company size, location, and engagement level.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Which contacts to analyze — e.g. 'my leads', 'contacts added this month' | |
| campaign_id | No | Analyze contacts in a specific campaign |
Changes observed during successful MCP inspections.
Input schema / properties / campaign_id / descriptionPrevious value: -"Analyze contacts enrolled in a specific campaign (alternative to query)"New value: +"Analyze contacts in a specific campaign"Input schema / properties / query / descriptionPrevious value: -"Which contacts to analyze in plain English — e.g. 'my leads', 'contacts added this month', 'customers in EU'"New value: +"Which contacts to analyze — e.g. 'my leads', 'contacts added this month'"Input schema / properties / campaign_id / descriptionPrevious value: -"Analyze contacts in a specific campaign"New value: +"Analyze contacts enrolled in a specific campaign (alternative to query)"Input schema / properties / query / descriptionPrevious value: -"Which contacts to analyze — e.g. 'my leads', 'contacts added this month'"New value: +"Which contacts to analyze in plain English — e.g. 'my leads', 'contacts added this month', 'customers in EU'"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the agent knows it's safe. The description adds the context that it's 'AI analysis', implying computational processing, and lists the output dimensions. However, it does not disclose any potential latency, credit consumption, or that it might produce a report versus a structured list. Given the annotations cover the safety profile, this is acceptable but not rich.
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 a single, focused sentence that front-loads the tool's purpose and lists the analysis dimensions. No wasted words.
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 description is moderately complete: it explains the input scope (contact list) and expected output aspects (breakdown by key dimensions). However, it lacks details on the output format (e.g., report, JSON, etc.) and whether the analysis is synchronous or async. Given the absence of an output schema, additional clarity would help, but the core use case is clear.
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%, with both query and campaign_id having descriptive text. The tool description adds no parameter-specific detail beyond the schema, but the breakdown dimensions in the description help interpret what 'query' might filter. Baseline is 3.
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 clearly identifies the tool's function: performing AI analysis on a contact list, with specific breakdown dimensions (industry, title, company size, location, engagement level). This distinguishes it from sibling tools like search_contacts or export_contacts, which are retrieval/export operations. The verb 'analysis' is implicit but the noun phrase is specific.
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?
The description does not explicitly state when to use this tool versus alternatives like search_contacts or run_ai_report. Usage is implied by the name and description, but there is no guidance on prerequisites or when not to use it.
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.