AfterLaunch

Record a claim

record_claim

Destructive

Put one measured number the founder will stand behind in public into the claim library, so every later reply and growth marketing post can cite it with its caveat. WHEN: a real measurement lands and the founder says they would defend it. Record the NUMBER and its caveat together. Never record an estimate, a projection, a rival's figure, or anything you inferred rather than measured. Free; requires the 'act' scope. Recording the same claim twice replaces your earlier wording; a pinned claim is left as it is. WHAT COMES BACK: their top moves with move ids.

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": {
      "text": "<text>",
      "trigger": "<trigger>",
      "number": "<number>",
      "caveat": "<caveat>"
    },
    "name": "record_claim"
  }
}

Input Schema

Name	Required	Description
`held`	No	True to record it and block its use.
`text`	Yes	The claim in one sentence.
`caveat`	Yes	What it does not prove, against your own interest.
`number`	Yes	The measurement, with its unit and comparison.
`trigger`	Yes	Keywords saying when this claim is relevant.

Schema Changelog

Changes observed during successful MCP inspections.

AddedSep 2, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint false, destructiveHint true), the description adds material context: it is free, requires the 'act' scope, and de-duplication replaces earlier wording while leaving a pinned claim untouched — which actually explains the destructive surface. What it lacks is detail on the return payload ("their top moves with move ids" is terse and the pronoun is loose) and any note on what 'held' does at record time.

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?

Purpose is front-loaded in the first clause, then WHEN, exclusions, cost/scope, dedup behavior, and returns in a predictable order — every block earns its place. Minor deductions for density in a single paragraph and the ambiguous "their top moves" at the end.

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?

With no output schema, the description takes on the return-value burden itself (top moves with move ids), and it covers cost, required scope, and de-duplication semantics for a mutation tool with five parameters. An agent has enough to decide, construct the call, and predict what changes.

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 description coverage is 100%, so the five parameters are already documented in-structure and a baseline of 3 is appropriate. The description reinforces the important pairing ("Record the NUMBER and its caveat together") but adds nothing about 'trigger' keywords or the 'held' flag, which are the parameters an agent is most likely to misuse.

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?

"Put one measured number the founder will stand behind in public into the claim library" names a specific verb, the exact resource (a measured number), the destination (claim library), and its downstream use (replies and growth posts citing it with caveat). This is clearly a different artifact type than record_insight, record_content, or record_profile, so an agent can route reliably.

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?

The WHEN clause states the positive trigger precisely (a real measurement lands and the founder would defend it), and the negative list is explicit and unusually well-targeted: no estimates, projections, rival figures, or inferred values. That is a genuine when-not, not just implied usage.

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

All AfterLaunch 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.

Resources

Need Help?