Sliq

Apollo Enrich

apollo_enrich

Read-only

Pass all candidate domains at once — one call with the full list, not one call per domain. The tool fans them out to Apollo's /organizations/enrich endpoint in parallel (ThreadPoolExecutor, max 20 concurrent, well within Apollo's 1000 req/min limit), so a batch costs one tool round instead of N.

Org-only (company domains, not people). For person enrichment (work email, LinkedIn URL), use find_email instead.

Costs 1 Sliq credit per found=True result (free for found=False, free on BYO Apollo). Soft-fails on insufficient credits — already- enriched results are still returned.

Per-user 24h cache: any domain this user already enriched — in an earlier run_code sandbox, an earlier call, or an earlier run — is served from cache with no second Apollo call and no second charge (both found=True and found=False are cached). The input list is also deduped by canonical form before fan-out.

Each enriched company is also saved to your canonical company entities, queryable via query_companies. List of dicts, one per input domain, in the same order. Each is either: {found: True, name, domain, industry, employee_count, annual_revenue, founded_year, latest_funding_stage, total_funding, location, linkedin_url, description} OR: {found: False, queried_domain, message}

latest_funding_stage is Apollo's title-case display string (e.g. "Seed", "Series A", "Series B", ..., "Series Unknown", "Private Equity", "Post-IPO Equity", "Other") — passed through verbatim, NOT a lowercase_underscore enum. It is None/absent when Apollo has no funding data for the org. total_funding is a USD integer (Apollo defaults it to 0, not null, when absent). Apollo's funding coverage is patchy, especially for bootstrapped / PE-owned / privately-held companies. Callers gating on these fields should decide how to handle missing data — matches_icp includes-on-null rather than excludes, so legit rows with thin Apollo coverage aren't silently dropped, and normalizes case + separators when comparing the stage string.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`domains`	Yes	List of company domains (e.g. ["acme.com", "foo.io"]). Order is preserved in the return list. Duplicates (after canonicalization) are collapsed and the result is shared.
`on_behalf_of`	No	An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 19, 2026

addedInput schema / properties / on_behalf_of

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
+}

First observedSep 15, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare readOnlyHint=true, so the description carries the full burden and delivers: cost model (1 credit per found=True, free on found=False/BYO), soft-fail on insufficient credits, 24h per-user cache with dedup, and parallel fan-out details. This is exactly the kind of context beyond structured fields that earns a 5.

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 summary and logically grouped sections (cost, cache, returns) are well organized, but the returns block is long and the prose is somewhat verbose. Size is justified by complexity, yet a few sentences could be tightened.

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

Completeness5/5

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

Despite no output schema, the <returns> block fully specifies the dict shape for both found=True and found=False, and flags data-quality caveats (patchy funding coverage, title-case stage string, total_funding defaulting to 0, matches_icp null handling). Nothing an agent needs to call or interpret results is missing.

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 description coverage is 100%, so the baseline is 3. The description reinforces ordering and canonical-form dedup, but those are already stated in the schema's own domain param description, so it adds little net new parameter meaning.

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 (enrich company domains, batch org-only) and explicitly disambiguates from the sibling find_email ('For person enrichment... use find_email instead'). An agent can tell it apart from apollo_search/apollo_save without opening the schema.

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?

Explicit guidance on batching ('Pass all candidate domains at once — one call with the full list, not one call per domain'), the alternative for people (find_email), and the follow-up query path (query_companies). When-to-use and when-not-to-use are both covered.

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

All Sliq 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?