Skip to main content
Glama

Set type

set_type
Destructive

Sets what the project is: its type (what people do when its marketing works) and the switches on top of it (who buys it, where people get it, restricted goods, aimed at children, a team inside a big company, ads on or off). It changes what every week plans, so call it only after the owner said yes to this exact change; say what it would change first. null hands a part back to Marsell's reading. The types: shop: Shop: people buy products. For example a clothing brand, a food brand, an Etsy maker. paid_software: Paid software: people sign up and pay. For example an app, a SaaS, an AI tool. free_tool: Free or open tool: people download and use it. For example an open-source project, a free app, a developer tool. local: Local place or service: people come in or book nearby. For example a restaurant, a dentist, a plumber, a walking tour. client_work: Client work: people hire you for a job. For example an agency, a PR firm, a freelancer, a coach, a solo lawyer. channel: Channel or show: people follow what you put out. For example a YouTube channel, a podcast, a newsletter, a streamer. release: Release: people wishlist, then buy a book, album, film or game. For example a debut novel, an indie game, an album. course: Course: people enrol. For example a cohort course, a school, a bootcamp. event: Event: people come on a date. For example a conference, a club night, a meetup series. community: Community: people join. For example a Discord, a club, a paid membership. fundraiser: Fundraiser or charity: people give money. For example a GoFundMe, a nonprofit, a charity drive. campaign: Campaign: people sign, vote or act. For example a petition, an issue campaign, an advocacy group. A project may have a second type (type2), for example paid software with a free tool beside it. Free tools and campaigns start with ads off. situation_read or input.app.project shows the type now. It needs an act key.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "set_type"
  }
}

Input Schema

NameRequiredDescriptionDefault
adsNothe ads switch: on or off; null follows the type (free tools and campaigns start with ads off)
typeNothe project's type: what people do when its marketing works; null hands it back to Marsell's reading
type2Noa second type it also is (open core: paid software with a free tool beside it); null clears it
buyersNowho buys it: people, businesses or both; null hands it back
projectNoThe project's id or exact name. Optional when the account has one project.
sold_onNowhere people get it: own_site, marketplace, app_store, in_person, platform_profile; null hands it back
childrenNoaimed at children; null hands it back
enterpriseNoa team inside a big company; null hands it back
restrictedNorestricted goods it sells (an empty list says none); null hands it back

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, and the description adds real context on top: the change ripples into 'what every week plans,' approval must be obtained first, null reverts a field to Marsell's own reading, and free tools/campaigns default to ads off. The only weak spot is the unexplained 'It needs an act key,' which hints at an auth/precondition detail without saying what it is.

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?

Purpose and the approval warning are front-loaded correctly, but the twelve-entry type catalogue with two examples apiece is a long undifferentiated block that partly restates the schema enum. It is usable, yet a bulleted or tabular layout would deliver the same information far more scannably.

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?

A 9-parameter mutation tool with no output schema is covered well: what changes, what the downstream effect is, approval gating, null/reset behavior, defaults, and where to read the current state are all present. Missing only the return/confirmation behavior and the meaning of the 'act key' prerequisite.

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 3 is the floor, but the description earns more: it defines null semantics per field ('hands a part back to Marsell's reading' vs 'null clears it' for type2), gives the concrete open-core example for type2, and spells out the ads default. The 12 type definitions with real-world examples add meaning beyond bare enum labels.

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?

Opens with a specific verb+resource ('Sets what the project is: its type ... and the switches on top of it') and then enumerates exactly which switches (buyers, sold_on, restricted, children, enterprise, ads). No sibling tool in the list does project type configuration, and the description makes that unmistakable.

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?

Gives an explicit precondition rather than a bare 'use when': 'call it only after the owner said yes to this exact change; say what it would change first.' It also points at situation_read / input.app.project to inspect the current value before calling. It stops short of naming a when-not-to-use case or an alternative tool, so not 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.