Skip to main content
Glama
Sign In

AfterLaunch

by io.afterlaunch
OverviewDiscussionsAdmin

Record an insight

record_insight
Destructive

Write one durable fact about your user or their product into AfterLaunch's Memory, the record every growth and marketing draft is written from. WHEN: your user tells you something AfterLaunch could not have measured itself that will still be true next month. A standing preference, a rule about how they write, a fact not on the site yet, or what a shipped move actually earned. Record what LASTS. Never record chatter, a passing mood, a restatement of the Snapshot or Memory, or anything you inferred rather than heard. One sentence in the founder's own terms, 10 to 500 characters. Free; requires the 'act' scope. Recording the same insight twice replaces your earlier note; a pinned note is left as it is. WHAT COMES BACK: their top moves with move ids, without a second call.

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": {
      "insight": "<insight>",
      "kind": "<kind>"
    },
    "name": "record_insight"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYespreference = a standing choice about how they work. voice = how they write (a rule they approved goes to record_voice_rule). fact = something true about the product. outcome = what a shipped move earned.
insightYesThe durable insight, as one plain sentence in the founder's own terms.
source_move_idNoOptional growth move id (uuid), from list_feed, when the insight surfaced while working one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / kind / description
      Previous value: -"preference = a standing choice about how they work. voice = how they write. fact = something true about the product. outcome = what a shipped move earned."New value: +"preference = a standing choice about how they work. voice = how they write (a rule they approved goes to record_voice_rule). fact = something true about the product. outcome = what a shipped move earned."
  2. Changed3 schema fields changed
    • changedInput schema / properties / insight / description
      Previous value: -"The durable insight, as one plain sentence in the founder's own terms, e.g. \"Will not do cold outreach; every channel has to be something a customer opts into.\"."New value: +"The durable insight, as one plain sentence in the founder's own terms."
    • changedInput schema / properties / kind / description
      Previous value: -"preference = a standing choice about how they work. voice = a rule about how they write. fact = something true about the product or business. outcome = what a shipped move actually earned."New value: +"preference = a standing choice about how they work. voice = how they write. fact = something true about the product. outcome = what a shipped move earned."
    • changedInput schema / properties / source_move_id / description
      Previous value: -"Optional growth move id (uuid) this came out of, from list_feed. Pass it when the insight surfaced while working a specific move."New value: +"Optional growth move id (uuid), from list_feed, when the insight surfaced while working one."
  3. Added

TDQS

A4.4/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing dedup semantics (same insight twice replaces the earlier note, pinned notes untouched), cost ('Free'), required auth scope ('act'), and the exact return payload ('top moves with move ids, without a second call'). It is consistent with destructiveHint=true since replacement is a stated overwrite, though it does not say what happens to the pinned note's content or how replacement is matched (text vs. kind).

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?

Dense but front-loaded, with clear WHEN / constraints / WHAT COMES BACK structure so an agent can scan it. A few phrases are redundant with the schema (the character limits) and the sentence flow is long, but nothing is padding in a way that hurts comprehension.

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 three-parameter write tool with no output schema, the description covers eligibility, exclusions, replacement behavior, auth scope, and the return value, which is everything an agent needs to call it correctly. No material gap remains.

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% and the kind enum already documents all four values, including the routing note to record_voice_rule. The description's 'one sentence in the founder's own terms, 10 to 500 characters' largely restates the schema's minLength/maxLength and field description, and it never mentions the optional source_move_id. Baseline 3 is appropriate.

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 one durable fact ... into AfterLaunch's Memory') and scopes it against siblings by directing approved writing rules to record_voice_rule and distinguishing this from the Snapshot or Memory itself. An agent can tell what belongs here versus record_claim or record_voice_rule without opening another 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 an explicit WHEN condition (user states something unmeasurable that will still be true next month) plus enumerated positive cases (standing preference, writing rule, off-site fact, earned outcome) and explicit exclusions (chatter, passing mood, restatement of Snapshot/Memory, inference). It also names the sibling alternative for voice rules, so when-not guidance is covered, not just when.

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

All AfterLaunch toolsInspect
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.

Resources