Skip to main content
Glama
Sign In

SerpKite

by io.github.SerpKite
OverviewDiscussionsAdmin

Ask Gemini

gemini
Read-onlyIdempotent

Ask Google Gemini (gemini.google.com, as a logged-out user) and get its answer with the sources it grounded on. 3 credits; takes 5-30 s, a few up to 90; free if it fails. If it fails with upstream_timeout saying the answer is being finished in the background, call again with the same arguments within 10 minutes to receive it.

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": {
      "prompt": "<prompt>"
    },
    "name": "gemini"
  }
}

Input Schema

NameRequiredDescriptionDefault
trackNoBrands or domains to check the answer for (mentions: named in the text, cited, listed as a source or product)
promptYesThe message to the assistant (up to 4,000 characters)
countryNoAsk from this country, e.g. us, de, gb (answers, prices and shops follow it)
languageNoInterface language, e.g. en, de

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / country
      Added value: +{
+  "description": "Ask from this country, e.g. us, de, gb (answers, prices and shops follow it)",
+  "type": "string"
+}
    • addedInput schema / properties / language
      Added value: +{
+  "description": "Interface language, e.g. en, de",
+  "type": "string"
+}
    • addedInput schema / properties / prompt
      Added value: +{
+  "description": "The message to the assistant (up to 4,000 characters)",
+  "type": "string"
+}
    • addedInput schema / properties / track
      Added value: +{
+  "description": "Brands or domains to check the answer for (mentions: named in the text, cited, listed as a source or product)",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 20,
+  "type": "array"
+}
  2. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld/idempotent, and the description adds value beyond them: explicit credit cost, expected latency distribution with a tail, no-charge-on-failure policy, and detailed recovery semantics for upstream_timeout (call again with identical arguments within 10 minutes). That is the kind of operational detail an agent cannot get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with zero filler: what it does, what it costs/how long it takes, and how to recover from the one notable failure mode. The critical retry instruction is placed last where it will be read when an error occurs.

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?

No output schema exists, and the description still tells the agent what comes back (answer plus grounding sources), what it costs, how long it takes, and what to do on the specific recoverable error. Nothing required for correct invocation is missing.

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

Parameters3/5

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

Schema description coverage is 100% and the schema already explains prompt length, country/language examples, and the tracking semantics of 'track'. The description adds no parameter-level meaning of its own, so baseline 3 applies.

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 ('Ask') and named resource ('Google Gemini'), plus the return payload ('its answer with the sources it grounded on') and the scope qualifier 'as a logged-out user'. This clearly separates it from siblings like chatgpt, copilot, brave_ai and ai_mode without needing to open any schema.

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?

Gives operational context (3 credits, 5-30 s typical, free on failure) and a concrete retry path for the upstream_timeout case, which is useful implied guidance. However, it never states when to pick this over chatgpt, copilot or brave_ai, so the agent must infer the choice from model identity alone.

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

All SerpKite toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources