Skip to main content
Glama

apollo_email

One-off emails (outside sequences): prepare, follow, read. SENDING is apollo_act(op="send_email") — another tool, the one your client asks you to confirm: draft here never reaches anyone. BYO key only on EVERY op: search/content/stats read the key owner's OWN sent mailbox (bodies included), not Apollo's shared database — unlike organization/people search, a platform key here would leak someone else's inbox.

Args by op:

  • draft: contact_id required UNLESS in_response_to_emailer_message_id is set (thread reply). Optional subject, body_html, recipients ([{"email":, "contact_id":, "recipient_type_cd": "to"|"cc"|"bcc"}]), emailer_template_id, attachment_ids, enable_tracking, outreach_task_id. Does NOT send: apollo_act(op="send_email", message_id=…) does.

  • status: message_id — poll send status.

  • search: stats, reply_classes, sequence_ids, exclude_sequence_ids, keywords, date_range_mode (due_at/completed_at), date_min/date_max (YYYY-MM-DD), per_page, page.

  • content: ids (up to 10 SENT email ids) + body_format (plain/html).

  • stats: message_id — opens/clicks. ⚠️ Apollo doc says this needs a Master API key, not verified from this environment.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "op": "<op>"
    },
    "name": "apollo_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
opYes
idsNo
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
pageNo
statsNo
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
_run_idNoOBLIGATOIRE à chaque appel dès `run_start` ou `data_claim_next` : sans lui, l'écriture sur une ligne réservée est refusée. Hérité seulement si le serveur tient un run actif — n'y compte pas.
subjectNo
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
date_maxNo
date_minNo
keywordsNo
per_pageNo
_instanceNoInstance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
body_htmlNo
contact_idNo
message_idNo
recipientsNo
body_formatNoplain
sequence_idsNo
reply_classesNo
attachment_idsNo
date_range_modeNo
enable_trackingNo
outreach_task_idNo
emailer_template_idNo
exclude_sequence_idsNo
in_response_to_emailer_message_idNo

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

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 behavioral burden and does so: it discloses the draft/send split, that `search`/`content`/`stats` read the key owner's PERSONAL sent mailbox including bodies rather than Apollo's shared database, and flags that `stats` reportedly needs a Master API key with an honest 'not verified from this environment' caveat.

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?

The highest-stakes facts (draft never sends, BYO key required, mailbox privacy) are front-loaded before the per-op breakdown, and the 'Args by op' block is a clean structure for a multiplexed tool. It runs long and the per-op lists are terse to the point of being telegrams, 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?

For a 28-parameter multiplexed tool with no annotations and no output schema, this covers the operation menu, the safety/credential constraints, and per-op argument requirements well. What is thin is the return side: nothing says what `draft` yields (presumably a message_id for the follow-up send), what `status` distinguishes, or how `search` paginates.

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 only 18% across 28 parameters, and the description compensates substantially: it groups args by `op`, gives the recipient object shape with `recipient_type_cd` values, date format `YYYY-MM-DD`, the `date_range_mode` alternatives, the 10-id cap on `content`, and the conditional requirement on `draft`. Gaps remain — `reply_classes`, `enable_tracking`, `emailer_template_id`, `attachment_ids`, and `outreach_task_id` are named but not explained, and the `stats` array parameter is undocumented.

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?

The description opens with a specific scope statement — one-off emails outside sequences, covering prepare/follow/read — and immediately names the sibling that does the actual sending (`apollo_act(op="send_email")`). An agent can distinguish this from apollo_sequence, apollo_sequence_contacts, and apollo_act without opening any 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 when-to-use and when-not-to-use routing: `draft` here never reaches anyone, sending is another tool. It also states a hard prerequisite for every op (BYO key only) with the consequence spelled out, so the agent knows a platform key is disqualifying rather than merely suboptimal.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources