Skip to main content
Glama

Add a lead by hand

lead_create

Adds one lead that no call or chat captured, such as a walk-in, a referral or a number taken down by hand. Needs a phone number; name, email, notes, status (default NEW) and captured fields are optional. The lead stays in this organisation's leads: it is not pushed to a CRM and starts no follow-up messages. A reference (the caller's own id for the lead) makes a retry safe. The same phone number is not refused twice.

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": {
      "phone": "<phone>"
    },
    "name": "lead_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
emailNo
notesNo
phoneYesInternational format, e.g. +919876543210
dryRunNoIf true, return what would be saved without saving
fieldsNoExtra captured details, e.g. {"City":"Pune","Budget":"20L"}
statusNoPipeline status, default NEW
referenceNoYour own id for this lead; a second create with it returns the first lead

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Beyond the annotations it discloses real behavior: the lead is not pushed to a CRM, starts no follow-up messages, and duplicate phone numbers are accepted. The reference-based retry safety is a useful conditional-idempotency note that the idempotentHint=false annotation alone would not convey, and it is consistent with that flag since only the reference makes a retry safe.

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 with purpose, then requirements, side effects, and idempotency in a logical order with no filler. "The same phone number is not refused twice" is slightly oblique phrasing that could be stated more directly as duplicate numbers being allowed.

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 an 8-parameter mutation with a nested object and no output schema, the description covers what an agent most needs: required input, side effects, dedup stance, and the reference retry contract. It omits what a successful call returns beyond the reference case and does not mention dryRun, both of which remain inferable from the schema.

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?

With 63% schema coverage the description adds meaning: it identifies phone as the sole requirement, marks name/email/notes/status/fields optional, states the NEW default, and explains that reference is the caller's own id used for safe retries. dryRun and the nested fields shape are left to the schema, which documents them adequately.

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?

"Adds one lead that no call or chat captured" gives a specific verb (add), resource (lead), cardinality (one) and a clear capture channel, which separates it from call/chat-derived capture paths. It stops short of naming a sibling tool such as contact_create, so the boundary is inferred from wording rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The examples (walk-in, referral, number taken down by hand) make the intended situation concrete and the required phone number sets a clear precondition. There is no explicit "do not use when" or named alternative, so an agent must infer the edge cases itself.

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.