ic_search_contactsSearch for contacts by name, email, or custom attributes. Returns contact ID, name, email, and metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search by email, name, or other field |
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | Array of contacts matching the search query | |
| error | No | Error code if connection required | |
| message | No | Error message if connection required |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "data": {
+ "description": "Array of contacts matching the search query",
+ "items": {
+ "properties": {
+ "custom_attributes": {
+ "description": "Custom attributes",
+ "type": "object"
+ },
+ "email": {
+ "description": "Contact email address",
+ "type": "string"
+ },
+ "id": {
+ "description": "Contact ID",
+ "type": "string"
+ },
+ "name": {
+ "description": "Contact name",
+ "type": "string"
+ },
+ "phone": {
+ "description": "Contact phone number",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "error": {
+ "description": "Error code if connection required",
+ "type": "string"
+ },
+ "message": {
+ "description": "Error message if connection required",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "query": "john.doe@example.com"
+ },
+ {
+ "query": "Sarah Smith"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly, idempotent, non-destructive. The description adds value by specifying return fields (contact ID, name, email, metadata), though it omits pagination or limit details.
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: first states purpose and search criteria, second lists return fields. No extraneous words, front-loaded with key information.
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 simple search tool with comprehensive annotations and output schema, the description is nearly complete. Minor omission of result size or pagination behavior, but sufficient for most use cases.
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 a single 'query' parameter. The description enhances by mentioning 'custom attributes' as a search field, adding specificity beyond the schema's 'other field'.
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 states the tool searches for contacts by name, email, or custom attributes, and distinguishes from sibling tools like ic_get_contact which retrieves a single contact by ID.
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 implies when to use (searching contacts), but does not explicitly state when not to use or mention alternatives like ic_get_contact for known IDs.
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.
Several tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route factual questions to the same underlying catalog with unclear boundaries. Polymarket tools also overlap (bet_research, polymarket_edges, polymarket_arbitrage), and ai_visibility_check vs scan_competitor_ai_presence are nearly the same operation.
Most tools follow a readable snake_case verb_noun pattern (ask_pipeworx, entity_profile, resolve_entity, list_subscriptions). However, the set mixes two distinct naming families — ic_* for Intercom tools and pipeworx/* for the rest — and includes ambiguous generic names like remember/recall/forget that don't visually connect to the rest.
36 tools is far more than needed for an Intercom-focused server; the vast majority have nothing to do with Intercom and instead cover a sprawling Pipeworx data-research, prediction-market, and memory/subscription toolkit. The count alone is in the 'too many' range, and the scope mismatch makes it feel even more inflated.
For a server named Intercom, the surface is severely incomplete: only read/list/search operations exist for contacts and conversations, with no create, update, delete, send-message, or company-detail operations. The unrelated Pipeworx tools are fairly broad, but they don't compensate for the missing Intercom lifecycle coverage that the server name promises.