Skip to main content
Glama

Choose where an app's agent runs

platform
Read-only

Where an app's agent runs: give requires (baa, gpu, private_network, edge, long_running, websockets, scheduled_jobs, large_uploads) with longest_turn_seconds and largest_upload_mb where they apply, and the goals you have. The answer is major (a platform is warranted: a requirement no curated runtime meets, a model provider it hosts, or an account held; name its system in a stack call next) or generic (any host meeting host_must will do, with the runtimes that meet it priced for a stated job). Every host ruled out comes with its own page's words; a host whose pages do not state a fact is neither ruled in nor out. A choice is made only when the rules settle it; otherwise it is the user's. 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: users_in (users_in); data_region (data_region); data_kind (data_kind); scale (scale); accounts (accounts, providers); clients (clients). On platform, a goal is sent by its own name (data_kind, data_region, users_in, scale, clients, accounts) with the values that call lists, and the model providers as providers; needs, regions and infra.vendors are not its parameters.

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": "platform"
  }
}

Input Schema

NameRequiredDescriptionDefault
scaleNoThe goal scale. With launch or live, a free tier that stops serving when idle is warned of.
clientsNoThe goal clients: where the app runs for its users.
accountsNoThe goal accounts: platforms (gcp, aws, azure, cloudflare), infrastructure products or vendors the user holds an account with. A platform held is warranted; a choice among several is made only among those held.
requiresNoWhat the app needs of a host. long_running needs longest_turn_seconds and large_uploads needs largest_upload_mb; either number given alone adds its requirement.
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. hipaa (for a covered entity) requires a business associate agreement; any but none, with ios among clients, adds Apple's disclosure rule.
providersNoThe model providers the app calls, as sent to /v1/resolve. A platform that hosts one is warranted.
data_regionNoThe goal data_region. No host's region is curated yet, so it is warned of, never filtered on.
largest_upload_mbNoThe largest file one request carries, in MB: a host whose request body is smaller is ruled out, and the answer warns to upload by a signed address.
longest_turn_secondsNoThe longest one request or run may take, in seconds: a host that stops one sooner is ruled out.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already establish a safe, closed-world read, but the description adds real behavior the agent could not infer: every ruled-out host comes with its own page's words, a host whose pages state no fact is neither ruled in nor out, and 'Counts as one call' flags the call-budget cost. It stops short of detailing the shape of the returned payload, though the two answer branches are described well enough to act on.

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?

Purpose and outcome branches are front-loaded, and nearly every clause carries actionable content within a size appropriate to a ten-parameter tool. The one blemish is redundancy: the goal list is enumerated twice, once with duplicated parentheticals like 'users_in (`users_in`)', and a single dense block makes the return-value and parameter-name information harder to scan.

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?

There is no output schema, so the description must explain the return value, and it does: the answer is `major` or `generic`, with what each means and what to do next. Combined with the decision rule, the discrepancy handling, and the parameter-usage guidance, an agent has everything needed to call it and interpret the result.

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?

With 100% schema coverage the baseline is 3, but the description goes beyond it by telling the agent that goals are sent by their own names (`data_kind`, `data_region`, `users_in`, `scale`, `clients`, `accounts`) with `providers` for model providers, and by explicitly excluding `needs`, `regions` and `infra.vendors` as parameters. That naming guidance prevents a class of malformed calls the schema alone would not catch.

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 precise statement of the decision being made ('Where an app's agent runs') and names the two possible outcomes (`major` vs `generic`) with the conditions that produce each. It also distinguishes itself from adjacent calls by saying a `major` answer means naming its `system` in a `stack` call next, so the agent knows this is the arbitration step, not the lookup step.

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

Usage Guidelines5/5

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

Explicit preconditions: 'have the ones that matter in hand from the plan, the repository or the user before calling', plus the decision rule 'A choice is made only when the rules settle it; otherwise it is the user's.' It also warns off misuse by stating that `needs`, `regions` and `infra.vendors` are not its parameters, and points to `stack` for the follow-up.

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