hs_search_contactsSearch contacts by name, email, or custom properties. Use when you need to find specific people in your database.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results (default 10, max 100) | |
| query | Yes | Search query (e.g., name or email) |
| Name | Required | Description | Default |
|---|---|---|---|
| total | No | Total number of matches | |
| results | No | Array of matching contact objects |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "results": {
+ "description": "Array of matching contact objects",
+ "items": {
+ "properties": {
+ "id": {
+ "description": "Contact ID",
+ "type": "string"
+ },
+ "properties": {
+ "description": "Contact properties",
+ "type": "object"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "total": {
+ "description": "Total number of matches",
+ "type": "number"
+ }
+ },
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "query": "john@example.com"
+ },
+ {
+ "limit": 20,
+ "query": "Sarah Smith"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds search scope but no additional behavioral traits beyond annotations. No contradiction with annotations.
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 that are front-loaded with the core action and usage context. No unnecessary words.
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?
Given the presence of output schema and comprehensive annotations, the description covers the primary use case. Could mention that it returns matching contacts, but not essential.
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 covers both parameters (query, limit) with descriptions. The description adds semantic value by indicating searchability by custom properties, which is not in 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?
The description clearly states the action (search), resource (contacts), and criteria (name, email, custom properties). It differentiates from sibling tools like hs_list_contacts by targeting specific people.
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?
Provides a basic usage context ('when you need to find specific people') but does not explicitly state when not to use or mention alternatives like hs_get_contact for single contact by ID.
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 are near-duplicates or overlapping entry points: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all serve overlapping query/discovery purposes. The polymarket tools and HubSpot tools are more distinct, but the set as a whole has fuzzy boundaries between many members.
Naming is inconsistent across the set: HubSpot tools use an hs_ prefix, Pipeworx tools mostly use bare verbs (ask_pipeworx, recall, forget), and other tools mix styles (ai_visibility_check, generate_llms_txt, polymarket_edges). The hs_* subset is consistent, but overall there is no single predictable pattern.
38 tools is too many for the apparent scope, especially since the server is named 'Hubspot' but only 6 of the tools are HubSpot-specific. A large portion of the catalog covers unrelated Pipeworx data access, prediction markets, memory, and npm scanning, making the set feel bloated and unfocused.
The HubSpot portion of the tool set is read-only: it can get, list, and search companies/contacts/deals, but has no create, update, or delete operations, leaving obvious lifecycle gaps. If the intended domain is actually Pipeworx/data research, the HubSpot tools seem like an unrelated afterthought, so the surface is incomplete for either interpretation.