Skip to main content
Glama

Check model key credit

check_model_credit
Read-onlyIdempotent

Ask each model key the workspace's agents run on whether its account can pay, with a billed request: a one-token answer for an OpenAI or Anthropic key (about a thousandth of a cent), and for an OpenRouter key the model and output limit of each default agent (less than a hundredth of a cent), which OpenRouter refuses when the balance cannot pay for the full output. willFail is true when the key the default agents use cannot pay: a mission started now stops at its first request. warning is the sentence to show the person.

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": "check_model_credit"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the readOnly/idempotent annotations, the description discloses the key behavior an agent could not otherwise know: the check spends real money with a billed request, including per-provider cost magnitude (a thousandth to a hundredth of a cent) and that OpenRouter rejects the probe when the balance cannot cover full output. It also explains the meaning of willFail and warning, which compensates for the absent output schema. Minor tension with readOnlyHint (a charged request is a side effect), but it does not modify workspace state, so this is not a contradiction.

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 substance is dense and relevant, but it is delivered as one long run-on sentence followed by a terse two-clause sentence, mixing purpose, pricing, provider quirks, and return-field semantics without clear ordering. It could be front-loaded and split for faster scanning.

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?

With no output schema, the description must carry return-value semantics, and it does explain willFail and warning, plus the per-provider nature of the probe results. It stops short of describing the overall response shape (for example, how per-key results are surfaced), leaving a small gap.

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?

The tool takes zero parameters, so there is no parameter meaning to add and the baseline is 4. The description does not manufacture irrelevant argument details.

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 specific verb and resource: probe each model key the workspace's agents run on to see whether its account can pay, via a real billed request. That is far more precise than a generic billing check and implicitly distinguishes it from things like get_billing, though no sibling is named explicitly.

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?

Usage is only implied: the willFail explanation ('a mission started now stops at its first request') hints that you call this before starting a mission, but there is no explicit when-to-use, when-not-to-use, or pointer to an alternative such as get_billing or list_credit_offers.

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.