Skip to main content
Glama

gflow_get_credits

Read the Google Flow credit balance for one saved profile or all profiles before choosing an account for generation; no credits are spent.

Instructions

Read the current Google Flow credit balance for one saved profile or all profiles - the number Flow's account menu shows. Read directly from flow.google.com with the profile's saved session (no browser) when Flow accepts it; otherwise read in that profile's browser (one browser launch per profile, sequential for all_profiles). The direct read is off on macOS by default, behind a proxy, or with GFLOW_CLI_WIRE_READS=0. HTTP 429/503 returns a retryable error with no browser fallback: wait, do not loop. Spends no credits. Set all_profiles=true when choosing an account for generation; partial profile failures remain visible in the result. Set refresh=true to renew a signed-out session (rewrites that profile's saved cookies) in a headless browser and read again (slower - one more Chrome launch per signed-out profile; a revoked session still needs gflow auth login). The tier fields (sku, service_tier, user_paygate_tier, subscription_credits) are always null: flow.google.com does not report them.

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": "gflow_get_credits"
  }
}

Input Schema

NameRequiredDescriptionDefault
profileNodefault
refreshNo
all_profilesNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.86.0
    • addedInput schema / properties / refresh
      Added value: +{
      +  "default": false,
      +  "title": "Refresh",
      +  "type": "boolean"
      +}
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full behavioral burden, and it does: it discloses that no credits are spent, the two read paths (direct session-based vs. one Chrome launch per profile), the conditions that disable the direct read (macOS default, proxy, GFLOW_CLI_WIRE_READS=0), and that 429/503 returns a retryable error with no browser fallback and should not be looped. It also warns that partial profile failures stay visible and that refresh rewrites saved cookies.

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?

It is a single dense paragraph, but the core statement is front-loaded and nearly every clause adds operating detail. Some env-var and 'wire reads' jargon compresses poorly and the browser-fallback facts are packed tightly, costing a point on readability.

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?

An output schema exists, so return values needn't be described, and the description still covers the one thing the schema can't convey: that the tier fields are always null. For a read-only balance tool with three optional parameters, no operational detail an agent needs is missing.

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?

Schema description coverage is 0%, yet the description supplies meaning for all three parameters: profile via "that profile's browser" and per-profile cookies, all_profiles via the sequential one-launch-per-profile behavior, and refresh via its cost and side effect (rewrites saved cookies in a headless browser, slower). It even pre-empts confusion about tier fields by explaining they are always null.

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?

States a specific verb and resource (read the Google Flow credit balance) and an explicit scope (one saved profile or all profiles), with an anchor the agent can reason about ('the number Flow's account menu shows'). That distinguishes it from siblings like gflow_usage_stats without the agent opening either schema.

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 conditional guidance for both optional flags: all_profiles=true is for choosing an account for generation, and refresh=true is for renewing a signed-out session. It also names the escape hatch for a revoked session (`gflow auth login`). It never states a when-not case, e.g. that calling it repeatedly is pointless when balance is not a selection criterion, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.