EvenLeads

Draft a message to a lead

draft_reply

Write a first message for one lead, in the tone set on its campaign: either a private message to the author or a public reply under the post. Returns the text and a link that opens the right place to send it (with the text filled in where the platform allows). Nothing is sent: the user sends it themselves. Each draft counts toward the reply drafts in the user's EvenLeads plan.

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": {
      "lead_id": "<lead_id>"
    },
    "name": "draft_reply"
  }
}

Input Schema

Name	Required	Description	Default
`type`	No	direct_message (private, default) or comment (public reply under the post).
`lead_id`	Yes	The id of a lead in the user's account.

Output Schema

Name	Required	Description	Default
`send`	No
`text`	No
`type`	No
`lead_id`	No
`post_url`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A4/5.0

Behavior3/5

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

Adds real value beyond the annotations: nothing is sent (the user sends it), a link with prefilled text is returned, and each draft consumes plan quota. However, 'Nothing is sent' sits somewhat awkwardly against readOnlyHint=false, and the description never explains what is actually persisted or why the call is non-idempotent, leaving the most consequential behavior partly opaque.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with what is produced, followed by what is returned and what it costs. No filler and nothing repeated from the schema or annotations verbatim.

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 non-destructive mutation with full schema coverage and an output schema, this covers the essentials: scope, return value, side-effect boundary, and quota impact. The remaining gap is whether drafts are stored or regenerating creates duplicates, which the non-idempotent hint leaves unexplained.

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 both lead_id and the mode enum are already documented. The description adds only the useful nuance that tone is inherited from the lead's campaign rather than supplied as a parameter; it offers no new syntax or constraints on lead_id or the enum.

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 ('Write a first message for one lead') plus the two output modes (private message vs public reply under the post). An agent can tell immediately that this is a per-lead drafting tool, distinct from the read/list siblings such as get_my_leads or list_my_campaigns.

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?

Clear context for when to use it: a first message, for exactly one lead, with the mode choice driven by whether a private or public touch is wanted. It doesn't name alternatives or state when not to use it (e.g., follow-ups, bulk drafting), so it stops short of the top score.

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

All EvenLeads tools Inspect

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.