Buyer Signals

Draft a follow-up with a reason to reply

draft_follow_up

Read-onlyIdempotent

Use this when the user wants a reply to one buying signal, such as "draft a reply to the first post" after find_buying_intent. Pass service and signal, one find_buying_intent or weekly_brief result whole, as it came, for example {"service": "SEO audit", "signal": {"source": "hackernews", "url": "https://news.ycombinator.com/item?id=1", "date": "2026-10-20", "label": "intent", "signals": ["looking for"], "quote": "Looking for an SEO audit for our shop"}}. Returns a 3-line draft built from the result's company, role, stack or quote, the reason to reply and checks before sending; a result without its company or quote is refused. Plain rules, no AI model. Draft only: it sends nothing, opens no link, has no recipient and fills in no name. Not for finding leads (use find_buying_intent).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "signal": {
        "url": "https://wordpress.org/plugins/ubersuggest-seo-tools/",
        "date": "2026-10-21",
        "label": "partner_fit",
        "source": "partners",
        "company": "Ubersuggest SEO Tools"
      },
      "service": "SEO audit"
    },
    "name": "draft_follow_up"
  }
}

Input Schema

Name	Required	Description	Default
`signal`	Yes	One result from find_buying_intent or weekly_brief, passed as it came. Its source, url, date, label, signals, company, role, stack and quote are read. hn_hiring, job_changes and partners results need their company, and post results their quote: the draft names them, and a signal without one is refused
`service`	Yes	The service you sell, as in find_buying_intent, such as "SEO audit"

Output Schema

Name	Required	Description
`sent`	Yes	Always false: this tool sends nothing
`as_of`	Yes	Date of this answer (UTC, YYYY-MM-DD)
`draft`	Yes	The three lines joined by line breaks, to edit and send yourself
`lines`	Yes	The draft in three lines: the opener, the useful line, the disclosure or easy close
`checks`	Yes	What to do before sending
`notice`	Yes	What the draft is and is not. Pass it on
`reason`	Yes	One line on why this lead has a reason to reply now
`status`	Yes
`service`	Yes
`based_on`	Yes
`lead_source`	Yes	The buying-signal source to store with a reply sent from this draft

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 4, 2026

addedInput schema / examples

Added value: +[
+  {
+    "service": "SEO audit",
+    "signal": {
+      "company": "Ubersuggest SEO Tools",
+      "date": "2026-10-21",
+      "label": "partner_fit",
+      "source": "partners",
+      "url": "https://wordpress.org/plugins/ubersuggest-seo-tools/"
+    }
+  }
+]

Changed7 schema fields changedNov 4, 2026

changedInput schema / properties / signal / description

Previous value: -"One result from find_buying_intent or weekly_brief, passed as it came. Only its source, url, date, label and signals are read; the quote is ignored"New value: +"One result from find_buying_intent or weekly_brief, passed as it came. Its source, url, date, label, signals, company, role, stack and quote are read. hn_hiring, job_changes and partners results need their company, and post results their quote: the draft names them, and a signal without one is refused"

addedInput schema / properties / signal / properties / company

Added value: +{
+  "description": "The result's company: needed for hn_hiring, job_changes and partners",
+  "maxLength": 200,
+  "type": "string"
+}

addedInput schema / properties / signal / properties / quote

Added value: +{
+  "description": "The result's quote: needed for hackernews, github and stackexchange",
+  "maxLength": 300,
+  "type": "string"
+}

addedInput schema / properties / signal / properties / role

Added value: +{
+  "description": "The result's role, for hn_hiring",
+  "maxLength": 200,
+  "type": "string"
+}

addedInput schema / properties / signal / properties / stack

Added value: +{
+  "description": "The result's stack, for hn_hiring",
+  "items": {
+    "maxLength": 80,
+    "type": "string"
+  },
+  "maxItems": 20,
+  "type": "array"
+}

addedOutput schema / properties / based_on / properties / company
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / based_on / properties / quote
```
Added value: +{
+  "type": "string"
+}
```

AddedNov 3, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: it discloses the 3-line output shape, that it is deterministic ('Plain rules, no AI model'), the refusal path when company or quote is missing, and the no-side-effects boundary ('sends nothing, opens no link, has no recipient'). That refusal rule is behavior an agent cannot infer from any structured field.

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 the trigger condition and the pass-through example before the return-value and boundary clauses, which is the right order. The inline JSON example is long and partially duplicates the schema's own examples array, so a little space is not fully earned.

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 two-parameter tool with a nested object and a published output schema, the description covers trigger, input shape, refusal cases, and side-effect boundaries. An agent has everything needed to call it correctly and to predict what it will and will not do.

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 real semantics by requiring the signal be passed 'whole, as it came' rather than reconstructed, and by calling out that hn_hiring/job_changes/partners results need company while post results need quote. It mostly restates the nested schema description, which keeps it below a 5.

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: draft a follow-up reply to one buying signal, and names the reason-to-reply framing. It explicitly separates itself from find_buying_intent ('Not for finding leads'), so an agent can route between the two siblings without reading 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?

Gives the triggering condition ('when the user wants a reply to one buying signal'), a concrete user phrasing ('draft a reply to the first post'), the prerequisite step ('after find_buying_intent'), and an explicit exclusion pointing to the correct alternative tool. All the when/when-not information is present.

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

All Buyer Signals 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.