Skip to main content
Glama

Add to my agent

want
Idempotent

Add something to your human's btw agent. Takes a link or an ASIN plus their email; a new email gets an agent. A hotel link becomes a stay (give month, and nights if known), a subscription link becomes software (give plan), anything else is gear. Or set type and the fields outright: stay needs hotel and month, home needs job and zip, software needs product and plan. Their agent starts watching it and the reply says how many other agents already want it. If you already read a page yourself, pass asins instead of a link. btw doesn't buy from Amazon. The link is how we know what you want; the group price comes from the brand.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
jobNohome: solar, home-battery, ev-charger, heat-pump, roof, windows, sauna-install, other
urlNoa product, hotel, or subscription link
zipNohome: five digit US zip
asinNoan Amazon ASIN, 10 letters and digits
nameNogym: the gym or studio name
noteNohome or stay: a short note
planNosoftware: individual, family, team, other
typeNoskip auto-detection and say the type
asinsNoASINs you read off a page yourself, up to 100
emailYesyour human's email, same as the waitlist
hotelNostay: hotel name or link
monthNostay: month as YYYY-MM
nightsNostay: nights, if known
productNosoftware: product name or link

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • addedInput schema / properties / hotel
      Added value: +{
      +  "description": "stay: hotel name or link",
      +  "maxLength": 200,
      +  "type": "string"
      +}
    • addedInput schema / properties / job
      Added value: +{
      +  "description": "home: solar, home-battery, ev-charger, heat-pump, roof, windows, sauna-install, other",
      +  "maxLength": 40,
      +  "type": "string"
      +}
    • addedInput schema / properties / month
      Added value: +{
      +  "description": "stay: month as YYYY-MM",
      +  "maxLength": 7,
      +  "type": "string"
      +}
    • addedInput schema / properties / name
      Added value: +{
      +  "description": "gym: the gym or studio name",
      +  "maxLength": 80,
      +  "type": "string"
      +}
    • addedInput schema / properties / nights
      Added value: +{
      +  "description": "stay: nights, if known",
      +  "maximum": 60,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / note
      Added value: +{
      +  "description": "home or stay: a short note",
      +  "maxLength": 200,
      +  "type": "string"
      +}
    • addedInput schema / properties / plan
      Added value: +{
      +  "description": "software: individual, family, team, other",
      +  "maxLength": 20,
      +  "type": "string"
      +}
    • addedInput schema / properties / product
      Added value: +{
      +  "description": "software: product name or link",
      +  "maxLength": 200,
      +  "type": "string"
      +}
    • addedInput schema / properties / type
      Added value: +{
      +  "description": "skip auto-detection and say the type",
      +  "enum": [
      +    "gear",
      +    "stay",
      +    "home",
      +    "software",
      +    "gym"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / url / description
      Previous value: -"a product link, Amazon or any store"New value: +"a product, hotel, or subscription link"
    • addedInput schema / properties / zip
      Added value: +{
      +  "description": "home: five digit US zip",
      +  "maxLength": 10,
      +  "type": "string"
      +}
  2. Added

TDQS

A4/5.0
Behavior4/5

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

The description goes beyond the annotations by explaining side effects: a new email creates an agent, the agent starts watching the item, and the reply reports how many other agents already want it. It also adds the caveat that btw doesn't buy from Amazon, though idempotency and failure behavior are left to the annotations.

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?

The description is information-dense and front-loaded with the core purpose and input format. The remaining sentences cover inference rules, explicit type fields, side effects, and caveats; a few terms like 'group price' and 'brand' are left unexplained, so it is not perfectly crisp.

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?

For a 14-parameter tool with full schema coveragechers, the description covers auto-detection, explicit types, required fields, side effects, and reply content. It omits the gym and gear field requirements and does not route to sibling tools, but those gaps are partially filled by the schema and enum.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaningful relationships not present in the schema: link or ASIN plus email, conditional field requirements per type, and the alternative asins array when the page was already read. Since schema description coverage is 100%, this extra relational guidance is genuinely valuable.

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 states a clear operation: 'Add something to your human's btw agent,' and elaborates with auto-detection rules and explicit type/field combinations. It does not distinguish itself from the dedicated want_gym, want_home, want_software, and want_stay sibling tools, so an agent still has to infer the relationship.

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

Usage Guidelines3/5

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

It provides concrete invocation guidance: pass a link or ASIN plus email, use asins if you already read a page, and either let link type auto-detect or set type with required fields. However, it never says when to choose this generic tool over the sibling want_* tools, nor does it state any exclusions.

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