Skip to main content
Glama

MisarReach MCP Server

by io.github.Misar-AI

start_autopilot

Start an autonomous outreach run: give the agent a goal and it finds, contacts and follows up with leads on its own.

This is the most consequential tool on this server. It is FIRE-AND-FORGET and it SENDS REAL MESSAGES TO REAL PEOPLE without returning for approval, so only start a run when the user has explicitly asked for one and understands the goal as written — the goal text is the entire brief. It returns a runId immediately; watch progress with get_autopilot_status.

CONSUMES AUTOPILOT CREDITS, plus search, enrichment and AI credits as it works. Requires an API key. Each call starts a SEPARATE run — calling twice runs two campaigns concurrently against the same goal.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
goalYesOutreach goal description (10-500 chars). E.g. 'Find and email 10 SaaS startup CTOs in London about our product'
workspace_idNoOptional workspace UUID to associate with this run

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Beyond annotations (readOnly=false, openWorld=true), the description discloses high-impact behaviors: it sends real messages without approval, consumes credits, requires an API key, and each call starts a separate run. It even labels itself 'the most consequential tool'—far beyond what annotations convey.

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?

The description is front-loaded with the essential action and then packs critical warnings into dense, imperative sentences. Every sentence serves a purpose—no fluff. Despite being long, it's tightly structured and appropriately verbose for the stakes.

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?

Given the tool's complexity (fire-and-forget, side-effects, credits, concurrency), the description covers all key aspects: what it does, what it returns, how to monitor, resource consumption, and the caution about multiple calls. No output schema exists, but the return value (runId) is disclosed explicitly. Complete for practical use.

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% for the two parameters, so baseline is 3. The description adds semantic value by stating 'the goal text is the entire brief,' which clarifies the goal parameter's significance and intent. This modest addition justifies a 4.

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 verb+resource: 'Start an autonomous outreach run' and clearly differentiates from siblings by emphasizing it is fire-and-forget, sends real messages, and returns a runId. It distinguishes itself from status and management tools like get_autopilot_status and list_autopilot_runs.

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?

Explicitly states when to use: 'only start a run when the user has explicitly asked for one and understands the goal as written.' It also provides warnings about not calling twice unless intended, and directs to get_autopilot_status for progress. This is strong guidance with clear exclusions.

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

All MisarReach MCP Server toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation5/5

Every tool targets a distinct resource and action: deals, leads, lists, autopilot runs, sales agent config, channels, and discovery. Even where tools share an entity, they are clearly differentiated (e.g., list_deals vs get_pipeline, update_deal vs move_deal_stage), with descriptions explicitly calling out when to use which.

Naming Consistency5/5

All 27 tools follow a strict verb_noun snake_case pattern: create, get, list, update, move, search, score, sync, start, submit, verify, etc. No mixed conventions or vague verbs—each name precisely signals its function.

Tool Count3/5

27 tools is on the heavier side and slightly exceeds the typical well-scoped range. However, the server covers multiple subdomains (deals, lead discovery, autopilot, sales agent, channels), so the count is justified by the breadth of the domain, though it feels dense.

Completeness4/5

Core lifecycles are covered: deals (create, list, update, move), leads (search, sync, list, enrich, score, verify, send), autopilot (start, list, status), sales agent (config, actions, process), and channels (status, update). Minor gaps include no delete tool for deals/leads and no stop-autopilot, but these are likely intentional and not blocking.

Resources