Skip to main content
Glama

CrunchJunkie

by io.crunchjunkie.app
OverviewDiscussionsAdmin

update_tracking_prompt

Change one tracking prompt's category (discovery, brand, competitor, shopping), intent, active flag, market, or its Follow-up-Survival follow-up question (followUpNarrower: the one question asked in the same conversation right after the prompt; only discovery or Commercial-intent prompts can have one; null clears it). Category moves the prompt between the brand and non-brand pools in dashboards and reports from the next render; no scan is triggered and history is untouched. The prompt text is not editable (a reworded prompt would keep the old history; a new prompt is added instead). Requires MCP write actions; without confirm:true it returns a preview.

Input Schema

NameRequiredDescriptionDefault
activeNotrue resumes a paused prompt (asked again by every scan started from then on; a trial workspace allows 10 active prompts per project); false pauses it: no future scans, it leaves a queued or running scan, every stored answer kept. Both write an internal timeline note.
intentNoNew intent.
marketNoMove the prompt to another market of its project, as a locale ("de-DE", "en-US", or a language alone such as "de"); list_prompts lists the markets. null, or the project's own market, puts it back on the project's market. Its stored answers keep the market they ran in; it is asked in the new market from the next scan. Refused while a scan of the project runs or is queued. Write a prompt in its market's language: moving it does not translate it.
confirmNoSet true to apply. Omit for a preview. With confirm:true, also pass the preview's previewToken.
categoryNoNew category. brand = the prompt names the tracked brand; competitor = it names a competitor or asks for alternatives to one; shopping = product/purchase intent; discovery = every other buyer question.
promptIdYesPrompt id (from list_prompts / get_prompt_details).
previewTokenNoWith confirm:true: the previewToken from this tool's preview (valid 15 minutes, once, for exactly the previewed arguments).
followUpNarrowerNoFollow-up Survival: the single follow-up asked in the same conversation after this prompt. It narrows the SAME shortlist ("Which of these …?"), in the prompt's language, with one added constraint. null or "" clears it. Answers to an earlier wording are no longer counted once it changes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • removedInput schema / additionalProperties
      Removed value: -false
  2. Changed1 schema field changed
    • changedInput schema / properties / followUpNarrower / description
      Previous value: -"Follow-up Survival: the single follow-up asked in the same conversation after this prompt. It must narrow the SAME shortlist (\"Which of these …?\"), in the prompt's language, with one added constraint. null or \"\" clears it. Answers to an earlier wording are no longer counted once it changes."New value: +"Follow-up Survival: the single follow-up asked in the same conversation after this prompt. It narrows the SAME shortlist (\"Which of these …?\"), in the prompt's language, with one added constraint. null or \"\" clears it. Answers to an earlier wording are no longer counted once it changes."
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: category change affects dashboard pools from the next render, no scan is triggered, history is untouched, market moves are refused while a scan is queued/running, stored answers keep their original market, and changed follow-up wording invalidates earlier answers. These are exactly the side effects an agent needs before mutating a live prompt.

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-loads the list of mutable fields and then moves to consequences and the preview requirement. Sentences are dense and parenthetical-heavy, but nearly every clause carries actionable information; only the follow-up parenthetical slightly overlaps the schema.

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 mutation tool with no output schema, the description covers the confirm/preview contract, permission requirement, and the downstream effects of each change type. An agent has everything needed to call it correctly on the first attempt.

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 already 100%, so the baseline is 3, but the description adds semantics absent from the schema — notably that only discovery or Commercial-intent prompts may carry a followUpNarrower, and what category changes do downstream. Some of the followUpNarrower explanation duplicates the schema text.

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?

Specific verb ('Change') plus resource ('one tracking prompt') and an explicit enumeration of the mutable fields (category, intent, active, market, followUpNarrower). It is clearly distinguished from siblings add_tracking_prompt and remove_tracking_prompt, and even states that the prompt text is not editable.

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?

Explains the preview-then-confirm workflow ('without confirm:true it returns a preview') and the write-permission requirement, so the agent knows how to invoke it safely. It implicitly routes text edits to adding a new prompt rather than editing, but does not explicitly name the alternative sibling tool for that case.

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

All CrunchJunkie 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