Apollo->Salesforce Lead mapper. No LLM. Strict-fail required fields. PASS/REPAIR/FAIL verdict.
Scored across 1 tool
With only a single tool in the set, there is no possibility of an agent confusing it with another tool; its purpose (Apollo contact → Salesforce Lead mapping) is stated explicitly and unambiguously.
The lone name `apollo_to_salesforce_lead` uses a clear, predictable snake_case source_action_target pattern. There is no competing convention to clash with, so consistency is trivially satisfied.
A one-tool surface is thin for a mapper domain that plausibly needs validation, batch/bulk mapping, field-mapping introspection, and reverse or multi-object mapping. Users have no way to preview, dry-run, or handle non-Lead objects without a separate server.
For the narrow Lead-mapping purpose the surface covers the core transform, but it stops at a single object with no bulk/batch variant, no mapping-schema inspection, and no Contact/Account/Opportunity targets, leaving common CRM integration workflows as dead ends.
Maps an Apollo contact payload to a Salesforce Lead object. Accepts the full Apollo CSV export column set. Strict-fail if FirstName, LastName, or Phone cannot be resolved. All other Salesforce fields are populated when source data is present, silently omitted otherwise. Returns a Deterministic Receipt (task_id, verdict, confidence, diff[]) embedded in every non-FAIL response.
| Name | Required | Description | Default |
|---|---|---|---|
| zip | No | Alternate ZIP key → PostalCode. | |
| cell | No | Primary phone (legacy key). Accepts E.164, 10-digit US, formatted strings. | |
| city | No | City → City. | |
| No | Contact email → Email. | ||
| phone | No | Apollo 'Phone' column — alternate primary phone key. | |
| state | No | State / province → State. | |
| title | No | Job title → Title. | |
| source | No | Apollo 'Source' column → LeadSource. | |
| street | No | Street address → Street. | |
| company | No | Company name → Company. | |
| country | No | Country → Country. | |
| website | No | Company website → Website. | |
| headline | No | LinkedIn headline captured by Apollo → Description. | |
| industry | No | Industry → Industry. | |
| keywords | No | Apollo keywords/tags → Description. | |
| No | Alternate LinkedIn key → LinkedIn__c. | ||
| employees | No | Alternate employees key. | |
| full_name | No | Full name — must have ≥2 whitespace-separated tokens. Use this OR provide first_name + last_name. Example: 'Jane Doe' | |
| job_title | No | Apollo 'Job Title' column → Title. | |
| last_name | No | Last name (Apollo split export). Use with first_name instead of full_name. | |
| prop_addr | No | Full property address string (legacy v1 key) → PropertyAddress. | |
| seniority | No | Apollo seniority level → Description. | |
| first_name | No | First name (Apollo split export). Use with last_name instead of full_name. | |
| work_phone | No | Apollo 'Work Phone' column — lowest-priority fallback. | |
| departments | No | Apollo departments string → Description. | |
| lead_source | No | Lead source string → LeadSource (mapped to Salesforce picklist values). | |
| person_city | No | Apollo 'Person City' column → City. | |
| postal_code | No | ZIP / postal code → PostalCode. | |
| twitter_url | No | Twitter/X URL → Twitter__c. | |
| account_name | No | Apollo 'Account Name' column → Company. | |
| linkedin_url | No | LinkedIn profile URL → LinkedIn__c. | |
| mobile_phone | No | Apollo 'Mobile Phone' column. Maps to MobilePhone if a primary phone exists. | |
| organization | No | Apollo 'Organization' column → Company. | |
| person_state | No | Apollo 'Person State' column → State. | |
| num_employees | No | Alternate employees key. | |
| annual_revenue | No | Annual revenue string, e.g. '$1.2M', '500000' → AnnualRevenue (number). | |
| person_country | No | Apollo 'Person Country' → Country. | |
| company_website | No | Apollo 'Company Website' → Website. | |
| person_postal_code | No | Apollo 'Person Postal Code' → PostalCode. | |
| number_of_employees | No | Employee count or range (e.g. '500-1000') → NumberOfEmployees. | |
| estimated_annual_revenue | No | Apollo estimated revenue → AnnualRevenue. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description takes on full responsibility for disclosing behavior. It clearly states the strict-fail conditions (FirstName, LastName, Phone), indicates silent omission for missing fields, and describes the return value (Deterministic Receipt). This covers key behavioral traits, though it could elaborate on FAIL response specifics or side effects.
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 four sentences, front-loaded with the core purpose. Each sentence adds value: input scope, strict-fail rule, omission behavior, and return format. There is no redundancy or filler, making it highly concise and well-structured.
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 41 parameters and no output schema, the description covers the essential context: what the tool does, its input expectations, failure behavior, and return receipt. However, it does not specify the structure of failure responses or elaborate on the receipt's fields, leaving a small gap given the tool's complexity.
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%, so the baseline is 3. The description adds meaningful semantic context by identifying which parameters are effectively required (FirstName, LastName, Phone) and how mapping behaves for missing data. This goes beyond the individual parameter descriptions and clarifies overall mapping rules.
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 uses a specific verb ('Maps') and clearly identifies the resource ('Apollo contact payload to a Salesforce Lead object'). It further specifies the input scope ('full Apollo CSV export column set'), making the tool's purpose unmistakable even without sibling comparison.
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 the primary use case (converting Apollo data into Salesforce Leads) and mentions the accepted input format ('full Apollo CSV export column set'). There are no explicit when-not-to-use or alternative tools, but given there are no siblings, the context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
apollo_to_salesforce_leadLeadOracle - 7-tool B2B lead intel MCP: enrichment, scoring, intent signals, ICP fit.
Prospect, enrich leads, and manage outreach sequences with Apollo.io.
Local business lead extraction with email + phone enrichment from Google Maps.
B2B lead generation, email verification, company enrichment, and agentic GTM Ops.
Add one secure layer between your agents and this server.
