Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Find Email

find_email
Read-only

Costs 1 Sliq credit per verified email; a BYO-Apollo key makes the Apollo leg free. The default chain runs MoltSets first and fills its misses with Apollo, so a contact that comes back {'error': ...} has been tried by both providers and is final — report those gaps and move on rather than re-running them.

When only one provider ran — a BYO-Apollo user's default, or an explicit 'apollo' pin — the other is still untried, and the result says so. That paid lookup is the user's call: in a background run with no one to answer, report how many were missed and stop; in an interactive chat, tell them the count and offer a MoltSets backfill (1 credit/hit), re-calling with provider='moltsets' on just those contacts only after they say yes.

A contact this user already resolved in the last 24h is served from a cache, so re-calling does not look up or charge again. One entry per input contact, in input order — either a hit dict (email, email_status, name, title, linkedin_url) or an {'error': ...} miss — followed by any warnings.

Each verified email is also written for you onto the person's canonical profile if it had none, which is the address every campaign tracking that person sends to and the one the Email column on the Output tab shows wherever they're on a list — you do not match or persist emails back onto rows yourself. It adds no one to an agent's list: when a person found here who isn't on it yet belongs there, record them with record_search_results.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contactsYesPeople to look up. Each needs a name, plus either an apollo_id or at least one of linkedin_url, company_name, or company_domain.
providerNoLeave unset (default) to let the chain pick — almost always right; don't pin a source the user didn't ask for. Set 'apollo' or 'moltsets' to pin a single source: 'apollo' runs Apollo alone (free with BYO Apollo, 1 credit/hit on Sliq's key); 'moltsets' runs MoltSets alone (1 credit per hit). Use 'moltsets' for the backfill the user approved after a run where only Apollo went out. Pinning skips the fallback, so coverage may be lower.
on_behalf_ofNoAn 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.

  1. Changed1 schema field changed
    • 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."
+}
  2. Changed3 schema fields changed
    • changedInput schema / properties / contacts / description
      Previous value: -"People to look up. Each must have name plus at least one of\n      linkedin_url, company_name, or company_domain."New value: +"People to look up. Each needs a name, plus either an\n      apollo_id or at least one of linkedin_url, company_name, or\n      company_domain."
    • changedInput schema / properties / contacts / items / description
      Previous value: -"A person to look up in Apollo."New value: +"A person to look up."
    • addedInput schema / properties / contacts / items / properties / apollo_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "The `apollo_id` from an `apollo_search` people result. With it, `name` can be the result's masked name and no other field is needed: Apollo matches the person by this ID."
+}
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint, so the description carries the real burden and does: per-hit credit cost, the free Apollo leg with a BYO key, the 24h result cache that prevents re-lookup and re-charge, provider-chain fallback semantics, and a genuine side effect (verified emails are written to the person's canonical profile and it does not add people to an agent's list). This is well beyond what the annotation conveys.

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?

Purpose is front-loaded and the summary/returns structure keeps the dense operational detail navigable. It is long, and the MoltSets-backfill instruction is restated from the `provider` schema description, which is mild redundancy rather than waste.

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?

With no output schema, the embedded returns block describes the exact response shape (one entry per contact in input order, hit dict keys, error misses, trailing warnings) plus the profile-write side effect and the routing to `record_search_results` for adding people to a list. Nothing material is left for the agent to guess.

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 100%, so baseline is 3, but the description adds real meaning: why `provider` should normally be left unset, what each pinned value costs, and that pinning skips fallback and lowers coverage. `contacts` batching and the parallel-lookup behavior are also described. It adds less for `on_behalf_of`, keeping it off a 5.

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

Purpose4/5

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

The description opens with a specific verb+resource ("Find email addresses for one or more people") and immediately clarifies the single-contact vs batch calling pattern, so an agent knows exactly what the tool returns. It does not explicitly differentiate itself from near neighbors like apollo_enrich or find_phone_number, so it stops short of a 5.

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?

It gives explicit when-to-use guidance (leave `provider` unset; don't pin a source the user didn't ask for), names the conditions that select alternatives (BYO-Apollo key, explicit 'apollo' pin, MoltSets backfill), and prescribes behavior for both unattended and interactive runs, including the user-approval gate before backfilling. Miss handling is spelled out precisely: report `{'error': ...}` contacts as final rather than re-running.

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

All Sliq toolsInspect
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