Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Apollo Save

apollo_save
Destructive

Save people as contacts or companies as accounts in the user's Apollo CRM, where they show in Apollo's web UI. Confirm with the user before calling this tool.

Each contact needs an email; it's the only required field. For a contact whose email you don't have, get it with find_email first, passing an apollo_search result's name and apollo_id, or the person's full name and company. Then save the real name and email it returns as {first_name, last_name, email, title, organization_name}.

For accounts, the result splits the count into "created" (new rows) and "existing" (already in the CRM — Apollo dedupes by domain); "saved" is their sum, so a re-save reads as saved == requested rather than a false failure.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeYes"contacts" or "accounts"
itemsYesList of dicts. For contacts: {first_name, last_name, email (required), title, organization_name}. For accounts: {name, domain}.
sequence_idNoOptional. If provided, contacts will also be added to this Apollo sequence for outreach.
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. Changed1 schema field changed
    • changedInput schema / properties / items / description
      Previous value: -"List of dicts. For contacts: {first_name, last_name, email (REQUIRED), title, organization_name}. For accounts: {name, domain}."New value: +"List of dicts. For contacts: {first_name, last_name, email (required), title, organization_name}. For accounts: {name, domain}."
  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=false / destructiveHint=true; the description goes well beyond by requiring user confirmation, disclosing that records become visible in the Apollo web UI, explaining domain-based dedupe, and pre-empting a false-failure interpretation by defining created + existing = saved. That is exactly the behavioral context the annotations cannot carry.

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-loads the core action in the first sentence and each following paragraph handles one mode (contacts, accounts). Slightly long, with a few clauses that could be tightened, but no sentence is filler.

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?

Covers the risky parts of a destructive write (confirmation, dedupe, count interpretation) without an output schema. The gap is that the return shape is explained only for accounts, leaving the contacts response (and any per-item failure reporting) unspecified.

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 100%, so item shapes, the required email, and the enum are already documented; the description mostly restates them. It does add genuinely new semantics (Apollo dedupes accounts by domain, and the find_email return maps directly onto the item fields), but it says nothing about `sequence_id`'s outreach side effect or `on_behalf_of`'s agency-client scoping beyond what the schema states.

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 ('Save people as contacts or companies as accounts in the user's Apollo CRM') plus the observable outcome ('where they show in Apollo's web UI'), with a clear split between the two modes. An agent can distinguish this from search/enrich/query siblings 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?

Gives explicit preconditions and routing: confirm with the user first, and for a contact without an email, call `find_email` with either an `apollo_search` result's `name`/`apollo_id` or the person's full name and company before saving. This is a concrete when-to-use and which-alternative-first instruction, not an inference.

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