contacts_listList your contacts in a stable order; page with nextBefore
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum saved contacts to return on this page | |
| before | No | The nextBefore of the previous page |
| Name | Required | Description | Default |
|---|---|---|---|
| contacts | Yes | ||
| nextBefore | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / limit / descriptionAdded value: +"Maximum saved contacts to return on this page"Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "additionalProperties": false,
+ "properties": {
+ "contacts": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "companyName": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "contactId": {
+ "type": "string"
+ },
+ "email": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "jobTitle": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "linkedin": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "name": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "organizationId": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "website": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "required": [
+ "contactId",
+ "name",
+ "email",
+ "jobTitle",
+ "companyName",
+ "website",
+ "linkedin",
+ "organizationId"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "nextBefore": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "required": [
+ "contacts",
+ "nextBefore"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and non-destructive. The description adds a meaningful behavioral guarantee: a stable order across pages, which is essential for correct cursor-based pagination. It does not mention auth or rate limits, but for a simple read-only list with an output schema, the added context is sufficient.
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, front-loaded sentence with no filler. It packs the verb, resource, stable-order guarantee, and pagination method into a compact form, making it easy for an agent to parse quickly.
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 list endpoint with complete schema descriptions, read-only annotations, and an output schema, the description covers the essential usage and pagination behavior. Return values are handled by the output schema, so the only real omission is explicit alternative routing, which is already captured in the usage_guidelines dimension.
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?
Both parameters are already fully documented in the schema with 100% coverage: limit has default/min/max, and before is defined as 'The nextBefore of the previous page.' The description merely echoes the before behavior and adds no new parameter meaning beyond the schema.
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?
Tautological: description restates name/title.
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?
It tells the agent this is for listing contacts and explains the pagination mechanism ('page with nextBefore'), which is useful for paging through results. However, it never states when to prefer this tool over contacts_create or the search-based siblings, nor does it give any exclusion conditions.
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.