Skip to main content
Glama

Send a request to CRM Connector

send_request

CRM Connector: Use when the person wants something CRM Connector does not offer yet: an integration with a system it does not connect (kind integration) or an AI agent for a system without one (kind ai_access). Emails the request to our team. Show what will be sent and get a yes first. Uses their account email when signed in. Not for a system that has an agent (use plan_ai_agent).

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": {
      "kind": "<kind>",
      "system": "<system>"
    },
    "name": "send_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesintegration for a system to connect, ai_access for AI Agents on a system.
nameNoThe person's name, when they gave it.
emailNoThe person's email, so CRM Connector can answer. Leave it out when they are signed in.
accessNoFor AI Agents: read to read records, read_write to also change them.
systemYesThe system the request is about, as the person names it.
companyNoThe person's company, when they gave it.
detailsNoWhat the person wants to do, in their own words: what should sync, or what the assistant should do in the system.
connect_withNoFor an integration: the system it should sync with, when the person said so.

Output Schema

NameRequiredDescriptionDefault
sentYes
messageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / access / description
      Previous value: -"For AI Agents: read (AI Analyst), or read_write (AI Agent) to also change records."New value: +"For AI Agents: read to read records, read_write to also change them."
    • removedInput schema / properties / budget
      Removed value: -{
      -  "description": "For AI Agents: the budget the person has in mind for the one-off setup, in their own words, when they gave one.",
      -  "maxLength": 120,
      -  "type": "string"
      -}
  2. First observed

TDQS

A4.4/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=false, so the agent knows this is a non-idempotent write-like action. The description crucially adds that a real email is sent to a human team and that the request must be shown and confirmed ("get a yes first") before sending — meaningful side-effect context beyond the annotations. It does not add much on failure modes or what happens after the email is sent, keeping it at a solid 3 rather than higher.

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?

It is a single dense paragraph that front-loads the trigger condition, then the kinds, then the confirmation rule, then the exclusion. Every clause carries information, though the packed run-on style makes it slightly harder to scan than a short bulleted structure would.

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?

The tool has 8 parameters, an output schema, and full annotation coverage; the description supplies the trigger, the kind taxonomy, the confirmation requirement, the signed-in email behavior, and the sibling exclusion. Nothing an agent needs in order to call this correctly is missing.

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 the baseline is 3, but the description adds routing meaning the schema does not: connect_with applies to the integration kind, access applies to ai_access, and email is only needed when the person is not signed in ("Uses their account email when signed in"). That cross-field conditional guidance is genuine added value.

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 states a concrete action and outcome — "Emails the request to our team" — and immediately scopes it to two request kinds (integration, ai_access) for capabilities CRM Connector lacks. It also names the sibling it is not (plan_ai_agent), so an agent can separate this from the planning tools without reading schemas.

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 an explicit trigger condition ("the person wants something CRM Connector does not offer yet"), maps the two enum kinds to their meanings, and adds a negative rule: "Not for a system that has an agent (use plan_ai_agent)". When-to-use, when-not-to-use, and the alternative are all present.

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