Vendo AI

Create an SDR search (Create & Start)

sdr_create_search

Creates an SDR search like the wizard's "Create & Start". Preferred: research_job_id from a finished sdr_get_research — every field defaults to the research profile, regions to its regions (or HQ country), all 24 hunters on, competitor pages saved, then the search is activated and the research's first buyers are copied in. Legacy: agent_id + name + target_regions (profile generated from the company profile if offer/ICP omitted). start=false creates a draft without hunting. Hunting is not billed per run; each usable contact costs 5 credits. Errors with 409 if an identical search was just created.

Input Schema

Name	Required	Description
`name`	No
`start`	No	Activate hunters right away (default true)
`agent_id`	No	Company profile id (legacy path, or must match the research's)
`languages`	No	Outreach languages; written into icp_summary
`icp_summary`	No	"Who buys". The decision-makers sentence and company-size line are added automatically.
`company_size`	No	e.g. "11–50 employees"; written into icp_summary as "Preferred company size: …"
`offer_summary`	No	"What you sell"
`target_cities`	No	Optional cities inside target_regions (use sdr_find_cities). Empty = whole countries.
`decision_roles`	No	Decision-maker job titles; used by Decision-maker matching and Website profile hunters
`signal_weights`	No
`target_regions`	No	ISO-2 countries or US states as CC:SUB, e.g. ['GB','US:FL']. At least one.
`enabled_sources`	No	Hunters to run. Omitted on create = all 24, exactly like the web wizard (includes paid engines and opt-in hunters).
`relevant_topics`	No
`research_job_id`	No
`competitor_pages`	No	Competitor LinkedIn page URLs (Competitor Engagement and Competitor Switching hunters)
`exclude_keywords`	No
`generation_model`	No
`industry_keywords`	No
`generation_reasoning`	No
`linkedin_search_queries`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed21 schema fields changedOct 26, 2026

addedInput schema / properties / agent_id / $ref
```
Added value: +"#/properties/research_job_id"
```

addedInput schema / properties / agent_id / description

Added value: +"Company profile id (legacy path, or must match the research's)"

removedInput schema / properties / agent_id / type
```
Removed value: -"string"
```

addedInput schema / properties / company_size

Added value: +{
+  "description": "e.g. \"11–50 employees\"; written into icp_summary as \"Preferred company size: …\"",
+  "type": "string"
+}

addedInput schema / properties / competitor_pages

Added value: +{
+  "description": "Competitor LinkedIn page URLs (Competitor Engagement and Competitor Switching hunters)",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 30,
+  "type": "array"
+}

addedInput schema / properties / decision_roles

Added value: +{
+  "description": "Decision-maker job titles; used by Decision-maker matching and Website profile hunters",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 20,
+  "type": "array"
+}

changedInput schema / properties / enabled_sources / description

Previous value: -"E.g. ['linkedin_jobs', 'connected_people']. Paid sources (ai_web_hunter, g2_reviews, tech_stack) are off by default."New value: +"Hunters to run. Omitted on create = all 24, exactly like the web wizard (includes paid engines and opt-in hunters)."

addedInput schema / properties / enabled_sources / items / description
```
Added value: +"Hunter source id (see sdr_list_hunters)"
```

addedInput schema / properties / enabled_sources / items / enum

Added value: +[
+  "linkedin_jobs",
+  "linkedin_company",
+  "linkedin_activity",
+  "ai_web_hunter",
+  "social_signal_hunter",
+  "crunchbase_rss",
+  "hn_hiring",
+  "g2_reviews",
+  "tech_stack",
+  "connected_people",
+  "email_enricher",
+  "linkedin_engagement",
+  "linkedin_job_change",
+  "linkedin_competitor_followers",
+  "cross_pool",
+  "people_pool",
+  "github_issues",
+  "adzuna_jobs",
+  "corporate_registries",
+  "web_news_radar",
+  "web_pulse_hunter",
+  "google_places",
+  "web_profile",
+  "local_listings"
+]

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

addedInput schema / properties / icp_summary / description

Added value: +"\"Who buys\". The decision-makers sentence and company-size line are added automatically."

addedInput schema / properties / languages

Added value: +{
+  "description": "Outreach languages; written into icp_summary",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / linkedin_search_queries

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "location_hint": {
+        "type": "string"
+      },
+      "query": {
+        "type": "string"
+      },
+      "rationale": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "query"
+    ],
+    "type": "object"
+  },
+  "maxItems": 50,
+  "type": "array"
+}

addedInput schema / properties / name / maxLength
```
Added value: +200
```
addedInput schema / properties / offer_summary / description
```
Added value: +"\"What you sell\""
```

addedInput schema / properties / research_job_id

Added value: +{
+  "format": "uuid",
+  "type": "string"
+}

addedInput schema / properties / start

Added value: +{
+  "description": "Activate hunters right away (default true)",
+  "type": "boolean"
+}

addedInput schema / properties / target_cities

Added value: +{
+  "description": "Optional cities inside target_regions (use sdr_find_cities). Empty = whole countries.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "admin1": {
+        "type": "string"
+      },
+      "admin1_code": {
+        "type": "string"
+      },
+      "country": {
+        "description": "ISO-2 country code; must be one of target_regions",
+        "maxLength": 2,
+        "minLength": 2,
+        "type": "string"
+      },
+      "lat": {
+        "type": "number"
+      },
+      "lng": {
+        "type": "number"
+      },
+      "name": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "country",
+      "name"
+    ],
+    "type": "object"
+  },
+  "maxItems": 100,
+  "type": "array"
+}

changedInput schema / properties / target_regions / description

Previous value: -"ISO-2 country codes the search targets, e.g. ['GB', 'US']."New value: +"ISO-2 countries or US states as CC:SUB, e.g. ['GB','US:FL']. At least one."

removedInput schema / required

Removed value: -[
-  "name",
-  "agent_id"
-]

First observedJul 28, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: it discloses automatic defaults from the research profile (regions, HQ country, all 24 hunters, competitor pages), post-create activation and buyer copying, credit cost (5 credits per usable contact, no per-run billing), and the 409 duplicate-search error. This is far beyond what structured fields provide.

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?

Front-loaded with the core action and preferred path before the legacy path, cost, and error details. Dense but almost every clause earns its place; the long parenthetical on defaults is dense enough to slightly slow parsing.

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

Completeness4/5

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

For a 20-parameter, unannotated, no-output-schema mutation tool, the description covers lifecycle, defaults, cost, and a key error case well. It does not state what is returned (e.g., the new search id) or point to follow-up tools like sdr_get_search, which would complete the picture.

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

Parameters4/5

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

Schema coverage is 55% across 20 params, and the description adds real meaning for the decision-critical ones (research_job_id path, start=false semantics, legacy target_regions) plus the hunter default. However, several params (signal_weights, relevant_topics, generation_model, exclude_keywords, industry_keywords, generation_reasoning, linkedin_search_queries) have neither schema descriptions nor narrative coverage, so a 5 is not warranted.

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 (Creates) and resource (an SDR search) and explicitly anchors it to the wizard's 'Create & Start' flow, which disambiguates it from sdr_preview_search, sdr_update_search, and sdr_start_research. The two-path structure (research_job_id vs legacy agent_id) tells an agent exactly what this tool does at a glance.

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

Usage Guidelines5/5

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

Explicitly names the preferred path (research_job_id from a finished sdr_get_research) and the legacy path (agent_id + name + target_regions), and states the condition for the draft variant (start=false). An agent has a clear decision rule for which parameter set to supply.

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?