Bulk-import up to 5,000 contacts in one call. By default, addresses that already exist are skipped rather than duplicated — pass update_existing: true to update them instead. Returns per-row results so you can see which rows were rejected and why.
| Name | Required | Description | Default |
|---|---|---|---|
| contacts | Yes | Contacts to import (max 5000) | |
| update_existing | No | Update contacts that already exist instead of skipping them (default false) |
Changes observed during successful MCP inspections.
Input schema / properties / contacts / items / properties / companyRemoved value: -{
- "type": "string"
-}Input schema / properties / update_existing / descriptionPrevious value: -"Update contacts that already exist (default true)"New value: +"Update contacts that already exist instead of skipping them (default false)"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations flag this as destructive and non-idempotent, and the description adds real substance on top: existing addresses are skipped by default rather than duplicated, update_existing switches to overwrite, and results are returned per row with rejection reasons. That explains the blast radius and partial-failure semantics the annotations cannot convey. It still does not say whether the call is atomic on failure or what the batch limit does when exceeded.
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?
Three tight sentences: the batch limit leads, the defaFault/override behavior sits in the middle, and the return shape closes. No filler and the most decision-relevant fact is front-loaded.
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?
With no output schema, the description supplies the return contract (per-row results with rejection reasons) itself, and it covers the batch cap, dedupe default, and the override flag. For a two-parameter bulk mutation whose annotations already state the safety profile, nothing needed to call it correctly is missing.
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 contacts and update_existing are already documented, including the default value on update_existing. The description restates and slightly enriches the duplicate-vs-update meaning but adds no syntax, format, or validation detail beyond the schema, so the baseline 3 applies.
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?
"Bulk-import up to 5,000 contacts in one call" gives a specific verb, resource, batch scope, and a hard limit, which implicitly separates it from the singular create_contact/update_contact siblings. It never names those siblings explicitly, so the differentiation must be inferred from the word "bulk".
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 explains the default duplicate-handling behavior and how to switch it with update_existing, which is useful operational context. It does not state when to choose this tool over create_contact (single) or update_contact, nor any prerequisites such as required fields or scopes.
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.