Create a contact if it doesn't exist, or update it if it does. Do not include sensitive personal data (health, financial, government ID, payment card, passwords).
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Contact email address | ||
| dry_run | No | Validate and show what would be sent without changing anything | |
| list_id | Yes | List ID | |
| last_name | No | Last name | |
| first_name | No | First name |
Changes observed during successful MCP inspections.
Input schema / properties / email / descriptionPrevious value: -"Contact email address,required"New value: +"Contact email address"Input schema / properties / list_id / descriptionPrevious value: -"List ID,required"New value: +"List ID"Input schema / properties / api_keyRemoved value: -{
- "description": "MailerCloud API key",
- "type": "string"
-}Input schema / properties / dry_runAdded value: +{
+ "description": "Validate and show what would be sent without changing anything",
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true. The description's only added behavioral content is the compliance constraint on sensitive data, which is genuinely useful. It does not explain what the destructive aspect means (e.g., overwriting existing field values, re-subscribing suppressed contacts) or how dry_run mitigates it.
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 sentences, front-loaded with the core behavior, zero filler. The safety constraint earns its place as a hard rule.
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?
There is no output schema, so the description should carry more weight. The compliance warning is a valuable addition, but gaps remain for a destructive upsert: what happens to existing fields, whether the dry_run flag is the safe preview path, and what a success response looks like.
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%, so the schema already documents all five parameters and the baseline is 3. The description adds no parameter-level meaning beyond the schema, and notably never mentions dry_run, the most consequential non-obvious parameter.
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?
States a specific verb+resource and defines the upsert semantics precisely ('create if it doesn't exist, or update it if it does'), which separates it from create_contact and update_contact without naming them. Not a 5 because sibling tool names are never referenced explicitly.
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 upsert framing implicitly tells the agent to use this when it doesn't know whether the contact exists, but there is no explicit 'use this instead of create_contact/update_contact when...' guidance and no prerequisites stated.
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.