Skip to main content
Glama

Choose a stack for an agent

stack
Read-only

For an agent that has to work with named systems (Linear, GitHub, Postgres…): what to connect for each, and which model to call. Give systems, target (local or cloud) and the harness the agent runs in; add model.providers to get a model too. Each system's choice is its owner's own MCP server or command-line tool, or none, picked by fixed rules from public records and not reviewed; warnings say what to read first, and config.mcp_json is a config to start from, with placeholders for every value the user supplies. A name that matches no system comes back in unknown_systems. Counts as one call. The answer depends on these goals; have the ones that matter in hand from the plan, the repository or the user before calling: cost (optimize, max_price, budget, calls_per_user_month); maker_origin (origin, origin_strict); users_in (users_in); data_kind (needs); scale (scale); accounts (providers, infra.vendors); clients (clients). On stack, the app's goals go by their own names at the top (data_kind, users_in, scale, clients), a model's parameters in model.constraints and providers in model.providers; infrastructure vendors are infra.vendors. The stack's own top-level needs are what the agent does (web_search, web_reading, browser), never a model's.

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": {
      "systems": "<systems>",
      "target": "<target>"
    },
    "name": "stack"
  }
}

Input Schema

NameRequiredDescriptionDefault
infraNoInfrastructure the agent runs on. Only read when `actions` or `needs` imply some.
modelNoThe providers to choose the agent's model on, as /v1/resolve would. Left out, no model is chosen and the rest is still answered.
needsNoWhat the agent needs beyond its systems: web_search, web_reading (fetching pages as text), browser. Each adds a part to `infrastructure`, as `code_execution` in `actions` adds a sandbox.
scaleNoWhat stage the app is at: prototype (for yourself), launch (to the public) or live. With launch or live, a system that admits only a few users before its vendor reviews the app is warned about (`approval_needed`).
usersNoHow many users the app has or expects, when known: `approval_needed` then compares it with each vendor's number.
preferNoFor a local agent and a system with a curated command-line tool: cli (default) chooses the tool, server its owner's server when there is one.
targetYesRequired. Where the agent runs. local: on a person's machine, with a shell, so a system's command-line tool can be the choice. cloud: only a remote server qualifies.
actionsNoWhat the agent does; default ["read"]. untrusted_input (it reads text from outside) together with write or code_execution is warned about.
clientsNoWhere the app runs for its users. A system read only on a device (Apple Health on iOS, Health Connect on Android) with none of its devices here is warned about (`on_device_only`).
harnessNoThe client the agent runs in, by id (the 400 for an unknown one lists them). It decides what is possible: a local server needs one that can start it, skills one that loads them. Left out, a client that can do all of it is assumed, and `assumptions` says so.
systemsYesRequired. The systems the agent works with, by id, name or alias, e.g. ["Linear", "github", "postgres"]. Each is matched exactly (case and punctuation aside) against the curated list; one that matches nothing comes back in `unknown_systems` and the rest are answered.
tenancyNosingle (default): the agent acts for one user or team. multi: it serves several tenants, so a server that takes one fixed key is warned about.
buildingNoWhat is being built, as skill tags. An owner's skills whose read carries more of them come first; a platform's owner's general skills are offered only when their read carries one. A skill not yet read keeps its place by date.
users_inNoThe goal users_in: where the app's users are (worldwide, eu: the EU among them, us: the US only). Recorded and listed in `assumed` when left out; no rule reads it yet, so it never changes the answer and is never asked.
data_kindNoThe goal data_kind. health, financial or hipaa adds zdr and no_training to the model's needs (when `model` is given), as /v1/resolve takes them; none adds nothing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / building
      Added value: +{
      +  "description": "What is being built, as skill tags. An owner's skills whose read carries more of them come first; a platform's owner's general skills are offered only when their read carries one. A skill not yet read keeps its place by date.",
      +  "items": {
      +    "enum": [
      +      "api",
      +      "auth",
      +      "automation",
      +      "billing",
      +      "browser",
      +      "charts",
      +      "ci",
      +      "cli",
      +      "cloud",
      +      "code-review",
      +      "containers",
      +      "databases",
      +      "debugging",
      +      "deployment",
      +      "docs",
      +      "email",
      +      "evals",
      +      "files",
      +      "frontend",
      +      "git",
      +      "images",
      +      "infrastructure",
      +      "kubernetes",
      +      "logging",
      +      "mcp",
      +      "migration",
      +      "ml",
      +      "mobile",
      +      "monitoring",
      +      "networking",
      +      "notebooks",
      +      "payments",
      +      "pdf",
      +      "performance",
      +      "presentations",
      +      "prompts",
      +      "refactoring",
      +      "scraping",
      +      "search",
      +      "serverless",
      +      "spreadsheets",
      +      "sql",
      +      "storage",
      +      "troubleshooting",
      +      "video",
      +      "web"
      +    ],
      +    "type": "string"
      +  },
      +  "maxItems": 8,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / clients
      Added value: +{
      +  "description": "Where the app runs for its users. A system read only on a device (Apple Health on iOS, Health Connect on Android) with none of its devices here is warned about (`on_device_only`).",
      +  "items": {
      +    "enum": [
      +      "web",
      +      "ios",
      +      "android",
      +      "desktop",
      +      "server"
      +    ],
      +    "type": "string"
      +  },
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / data_kind
      Added value: +{
      +  "description": "The goal data_kind. health, financial or hipaa adds zdr and no_training to the model's needs (when `model` is given), as /v1/resolve takes them; none adds nothing.",
      +  "enum": [
      +    "none",
      +    "health",
      +    "financial",
      +    "hipaa"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / scale
      Added value: +{
      +  "description": "What stage the app is at: prototype (for yourself), launch (to the public) or live. With launch or live, a system that admits only a few users before its vendor reviews the app is warned about (`approval_needed`).",
      +  "enum": [
      +    "prototype",
      +    "launch",
      +    "live"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / systems / maxItems
      Previous value: -12New value: +24
    • addedInput schema / properties / users
      Added value: +{
      +  "description": "How many users the app has or expects, when known: `approval_needed` then compares it with each vendor's number.",
      +  "exclusiveMinimum": 0,
      +  "maximum": 1000000000,
      +  "type": "integer"
      +}
    • addedInput schema / properties / users_in
      Added value: +{
      +  "description": "The goal users_in: where the app's users are (worldwide, eu: the EU among them, us: the US only). Recorded and listed in `assumed` when left out; no rule reads it yet, so it never changes the answer and is never asked.",
      +  "enum": [
      +    "worldwide",
      +    "eu",
      +    "us"
      +  ],
      +  "type": "string"
      +}
  2. Added

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations, the description discloses that choices come from fixed rules over public records, are not reviewed, and may include warnings, placeholder config, and `unknown_systems`. It also notes that the call counts as one call and that the answer depends on supplied goals. It does not discuss auth or rate limits, but it adds substantial behavioral context.

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 description is front-loaded and mostly free of filler, but it is very dense and uses long, semicolon-heavy sentences. The final paragraph clarifying goal and `needs` placement is valuable but hard to parse. The length is defensible for this tool's complexity, though the structure could be clearer.

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 15-parameter tool with no output schema, the description covers the essential behavior: inputs, goal dependencies, warnings, placeholder config, unknown systems, assumptions, and one-call billing. It does not fully describe the returned object's structure, but it is largely complete for correct invocation.

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 the baseline is 3, but the description adds meaningful disambiguation. It explains that app goals use top-level names, model constraints and providers live under `model`, infrastructure vendors under `infra.vendors`, and top-level `needs` are agent capabilities rather than model needs. That materially improves interpretation of a complex 15-parameter 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 clearly states a specific action and resource: for an agent working with named systems, it returns what to connect for each and which model to call. It is much more specific than the title alone, but it does not explicitly contrast itself with siblings such as resolve or plan, so it stops short of a 5.

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?

It gives clear usage context: use this for an agent that works with named systems, supply `systems`, `target`, and `harness`, and add `model.providers` when a model choice is wanted. It also tells the caller to gather relevant goals from the plan, repository, or user before calling. It does not state when not to use it or name alternatives, so it is 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.

Resources