Import up to 1000 contacts in one call. Existing numbers are automatically skipped, simplifying bulk contact management.
Import up to 1000 contacts in one call. Existing numbers are skipped.
| Name | Required | Description | Default |
|---|---|---|---|
| contacts | Yes | Contacts to import | |
| device_id | No | Device ID (e.g. D-XXXXX). Optional if the KIRIMI_DEVICE_ID environment variable is set. |
Changes observed during successful MCP inspections.
v1.1.0Input schema / properties / contacts / descriptionPrevious value: -"Array of contact objects"New value: +"Contacts to import"Input schema / properties / contacts / items / properties / nama / descriptionAdded value: +"Contact name"Input schema / properties / contacts / items / properties / nomor / descriptionAdded value: +"Phone number"Input schema / properties / device_id / descriptionPrevious value: -"Optional device ID to associate all contacts with"New value: +"Device ID (e.g. D-XXXXX). Optional if the KIRIMI_DEVICE_ID environment variable is set."v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It does disclose two useful traits: the 1000-contact cap and that existing numbers are skipped rather than overwritten. However, it says nothing about return values, partial failures, validation, or whether one bad contact aborts the whole batch.
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 two tight sentences with no filler. The primary function and batch limit are front-loaded, and the dedupe behavior follows immediately. Every sentence earns its place and can be scanned in one pass.
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?
For a two-parameter tool with 100% schema coverage, the core contract is present: batch contacts, a size limit, and dedupe behavior. However, with no output schema and no annotations, the agent is left without any indication of what the API returns on success or partial failure, so the context is incomplete.
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?
The schema already fully describes both parameters, so the baseline is 3. The description adds extra semantic value by stating 'existing numbers are skipped,' which effectively identifies 'nomor' as the deduplication key beyond the schema's plain 'Phone number' description.
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 opens with a specific action and resource: 'Import up to 1000 contacts in one call.' It clearly presents a batch operation with a hard capacity limit, which allows an agent to distinguish it from the singular sibling tool 'save_contact' without opening the schema.
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 1000-contact batch phrasing implies this is for bulk imports rather than single-contact saves, but the description never explicitly says to use 'save_contact' for one contact or states when this tool should be preferred. 'Existing numbers are skipped' adds context but no explicit when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.