Skip to main content
Glama

Relaunch decision checker

toolfound_relaunch_decision
Read-onlyIdempotent

Choose between a relaunch, a regular update, or more preparation from the size of the change and launch evidence you provide. Use it when you have already launched and are unsure whether to relaunch, post a regular update, or prepare more first. Returns one of three verdicts (plan a relaunch, publish a regular update, prepare before promoting) with the reasons and next actions, based only on the answers given. Returns an evidence-bounded result and the canonical web tool URL.

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": {
      "change": "<change>",
      "audienceChanged": "<audienceChanged>",
      "listingCurrent": "<listingCurrent>",
      "evidence": "<evidence>",
      "measurementReady": "<measurementReady>"
    },
    "name": "toolfound_relaunch_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
changeYesSize of the biggest change since your last launch: small is incremental improvements, major is a new workflow or a new audience, direction is a different product direction.
evidenceYesWhat you can show for the update: strong is a working release plus specific proof such as a demo or numbers, release is a working release only, none means it is not released yet.
listingCurrentYesyes if your public listing, screenshots and facts already match the product as it is today.
audienceChangedYesyes if the people you are targeting are different from the last launch.
measurementReadyYesyes if tracking, support ownership and a review date are already in place for the announcement.

Output Schema

NameRequiredDescriptionDefault
okYes
dataNo
linksYes
errorsNo
summaryYes
sectionsYes
canonical_result_urlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / audienceChanged / description
      Added value: +"yes if the people you are targeting are different from the last launch."
    • addedInput schema / properties / change / description
      Added value: +"Size of the biggest change since your last launch: small is incremental improvements, major is a new workflow or a new audience, direction is a different product direction."
    • addedInput schema / properties / evidence / description
      Added value: +"What you can show for the update: strong is a working release plus specific proof such as a demo or numbers, release is a working release only, none means it is not released yet."
    • addedInput schema / properties / listingCurrent / description
      Added value: +"yes if your public listing, screenshots and facts already match the product as it is today."
    • addedInput schema / properties / measurementReady / description
      Added value: +"yes if tracking, support ownership and a review date are already in place for the announcement."
  2. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive behavior, so the safety profile is covered. The description adds genuine behavioral context beyond that: three possible verdicts, accompanying reasons and next actions, output bounded strictly by the supplied answers, plus a canonical web tool URL. It does not mention determinism edge cases or how ties between signals are resolved, which keeps it at 3.

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 three-way choice is front-loaded, which is good, but the same list of options is restated in all three sentences (decision framing, when-to-use, and returned verdicts), which is redundant. The final sentence about the evidence-bounded result and canonical URL feels appended rather than integrated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and full enum documentation in the schema, the description need not explain return shapes, and it still summarizes the verdict set and the inclusion of reasons and next actions. Coverage of when the tool should not be used (pre-launch, no evidence at all) is the only notable omission.

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% and every parameter is a documented enum, so the schema already carries the semantics and baseline 3 applies. The description only gestures at two of the five inputs ('size of the change and launch evidence') and says nothing about listingCurrent, audienceChanged or measurementReady, so it adds little beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

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: choose among relaunch / regular update / more preparation, driven by change size and launch evidence. An agent can tell this is a decision-advisory tool rather than one that performs a relaunch (as toolfound_relaunch likely does). It stops short of naming any sibling explicitly, so differentiation is inferential.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use it when you have already launched and are unsure whether to relaunch, post a regular update, or prepare more first' gives a clear triggering condition, including the important precondition that a launch already happened. There is no explicit when-not clause or named alternative tool for the pre-launch case, so it falls short of a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources