Vendo AI

Search the people database

search_audience

Search the people graph for prospects matching include AND exclude filters (countries, cities, industries, positions, company sizes, tags, company keywords, language, freshness, must-have-email/LinkedIn/phone/booking link). PREVIEW only — returns aggregate counts and a small sample. Does not save anything, does not contact anyone, does not spend credits. Next: save_audience with the same filters.

Input Schema

Name	Required	Description
`city`	No
`tags`	No
`limit`	No	Sample size (max 100)
`cities`	No
`country`	No
`language`	No	Approximate language segment by country set, e.g. "russian"
`position`	No
`countries`	No	Country names, e.g. ["United Kingdom","Germany"]
`positions`	No	Job titles / roles, e.g. ["CEO","Head of Sales"]
`industries`	No
`maxAgeDays`	No	Only people added within the last N days
`searchMode`	No
`companySize`	No
`companySizes`	No
`exactKeyword`	No	Exact phrase (searchMode=exact)
`mustHaveEmail`	No
`mustHavePhone`	No
`semanticQuery`	No	Free-text description of the ideal person (searchMode=semantic)
`excludedCities`	No
`companyKeywords`	No	Keywords matched in company description / name / position
`excludeCountries`	No
`mustHaveLinkedin`	No
`excludedPositions`	No
`excludedIndustries`	No
`mustHaveBookingUrl`	No
`excludedCompanySizes`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed18 schema fields changedOct 26, 2026

addedInput schema / properties / city
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / companyKeywords

Added value: +{
+  "description": "Keywords matched in company description / name / position",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / companySize

Added value: +{
+  "enum": [
+    "startup",
+    "small",
+    "medium",
+    "large",
+    "enterprise"
+  ],
+  "type": "string"
+}

addedInput schema / properties / countries / description

Added value: +"Country names, e.g. [\"United Kingdom\",\"Germany\"]"

addedInput schema / properties / country
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / exactKeyword / description
```
Added value: +"Exact phrase (searchMode=exact)"
```

addedInput schema / properties / excludeCountries

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / excludedCities

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / excludedCompanySizes

Added value: +{
+  "items": {
+    "enum": [
+      "startup",
+      "small",
+      "medium",
+      "large",
+      "enterprise"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / excludedIndustries

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / excludedPositions

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / language

Added value: +{
+  "description": "Approximate language segment by country set, e.g. \"russian\"",
+  "type": "string"
+}

addedInput schema / properties / limit / description
```
Added value: +"Sample size (max 100)"
```

addedInput schema / properties / maxAgeDays

Added value: +{
+  "description": "Only people added within the last N days",
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / mustHaveBookingUrl
```
Added value: +{
+  "type": "boolean"
+}
```
addedInput schema / properties / position
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / positions / description

Added value: +"Job titles / roles, e.g. [\"CEO\",\"Head of Sales\"]"

addedInput schema / properties / semanticQuery / description

Added value: +"Free-text description of the ideal person (searchMode=semantic)"

First observedJul 28, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does so well: it discloses that this is a read-only preview returning aggregate counts plus a small sample, and that nothing is persisted or credited. It stops short of noting rate limits, cost profile, or how the sample size relates to `limit`.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action, then the preview guarantee, then the next step. The long parenthetical filter list is dense but each item maps to real parameters rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

It covers the return shape meaningfully for a tool with no output schema ('aggregate counts and a small sample'), which is the strongest part. However, for a 26-parameter search tool with 31% schema coverage, the absence of any guidance on searchMode selection or single-vs-plural field precedence leaves real gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 31% across 26 parameters, so the description must compensate; it enumerates the filter families and states the include-AND-exclude logic, which is real added meaning. But it says nothing about `searchMode` and its coupling to `exactKeyword`/`semanticQuery`, and leaves most individual params undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('search the people graph for prospects') plus the exact filter categories it accepts, and differentiates itself from the saving sibling by naming `save_audience` as the next step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly frames this as a preview/non-committal step ('does not save anything, does not contact anyone, does not spend credits') and routes to `save_audience` with the same filters. It doesn't distinguish itself from near-neighbours like `sdr_create_search` or `sdr_preview_search`, so the routing is clear but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Vendo AI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?