Skip to main content
Glama

Build our message for this segment

impact_build_segment_message
Read-only

Builds a segment-specific B2B message from a brief, flags proof gaps, maps champion and alternative choices, then returns the message and proof plan after buyer confirmation.

Instructions

Helps you decide how to build a message for one segment when sellers do not use it or buyers keep their current approach. Needs the product, segment, champion problem, alternatives, outcome, capability and proof. Returns proof gaps and current approach questions, champion and alternatives maps for human choices, then a message and proof plan after a pause. Optional agreed workshop claim is the starting point. Without a real customer result, buyer lines are unproved hypotheses and the next step is discovery questions. Chat carries the brief between calls. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing or invalid stage or brief fields return field-specific errors. The message stage requires the matching review receipt and confirmed choices. Missing real proof keeps buyer lines as unproved hypotheses. Use this instead of impact_craft_message when you need a staged segment workshop with confirmed champion and alternative choices.

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": {
      "stage": "<stage>",
      "brief": "<brief>"
    },
    "name": "impact_build_segment_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
briefYesThe segment brief carried unchanged between calls. Format is a JSON object. For example, {"product":"invoice review service","product_description":"checks invoice exceptions before approval","segments":["manufacturers with 200 to 500 employees"],"problem":"invoice exceptions delay month-end close","category":"manufacturing","alternatives":["the current manual review process"],"desired_outcome":"resolve invoice exceptions before month-end","capability":"checks invoice exceptions before approval","trigger":"an audit review due next quarter","measure":"days from invoice receipt to approval","sector":"manufacturing","proof":{"kind":"none"}}.
stageYesMap first. After the buyer chooses, call message with the same brief, its review receipt and confirmed choices. Format is text using one of the listed labels. For example, "map".
choicesNoThe champion and alternative choices confirmed by the buyer after reading the maps. Format is a JSON object. For example, {"confirmed":true,"champion":"finance director","champion_segment":"manufacturers with 200 to 500 employees","alternative":"the current manual review process"}.
review_receiptNoThe receipt from the map call, carried by chat. The server stores no brief. Format is text. For example, "copy the complete receipt returned by the map call".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.2.28

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real value beyond that: no sign-in, no stored inputs or outputs, hosted usage metadata recorded, a pause before the message stage, and field-specific validation errors. It does not describe output shape or the receipt's contents, which keeps 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.

Conciseness3/5

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

The purpose and the sibling routing are front-loaded, which is good, but the prose is dense and run-on. The point that missing proof leaves buyer lines as unproved hypotheses is stated twice, and the sign-in/storage/telemetry sentences could be tightened without losing information.

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?

For a complex, nested, two-stage tool with no output schema, the description covers what comes back (proof gaps, current-approach questions, champion and alternatives maps, then a message and proof plan), the pause, and the error behavior. An agent has enough to call it correctly and to know what to expect.

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 meaning the schema does not: the brief is carried unchanged between calls via chat, agreed_claim is an optional starting point for the chain, and the message stage requires the matching review receipt plus confirmed choices. That is genuine semantic guidance beyond the field descriptions.

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 and resource ('build a message for one segment') and states the triggering situation (sellers not used, buyers keep current approach). It explicitly distinguishes itself from the sibling impact_craft_message, so an agent can route without opening either 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?

It gives an explicit alternative rule: 'Use this instead of impact_craft_message when you need a staged segment workshop with confirmed champion and alternative choices.' It also states the stage ordering (map first, then message with the receipt and confirmed choices) and the fallback to discovery questions when proof is missing.

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