Skip to main content
Glama

Compare named providers head to head

compare_providers
Read-onlyIdempotent

Puts two or more named providers side by side on one benchmark, with each one's rank, measured value and success rate.

Use when the user names the candidates themselves: "Alchemy or Quicknode?", "is Helius faster than Triton for Solana?", "compare Across and Stargate on fees".

Find the benchmark slug with search_benchmarks first if you do not already have it. Providers the benchmark does not measure come back in missing: say they are not measured rather than implying they ranked badly. A provider measured but below the ranking floor comes back with rank null, which is also not a loss.

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": {
      "benchmark": "<benchmark>",
      "providers": "<providers>"
    },
    "name": "compare_providers"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNoAccess cohort on chain RPC benchmarks: 'public' (default, free no-key endpoints) or 'keyed' (API-key providers such as Alchemy, Quicknode, Chainstack, GetBlock). Named providers usually live on the keyed cohort.
chainNoOptional chain slice when the bench declares chains. Ignored on a bench that is already one chain, like solana-rpc.
regionNoOptional region slice when the bench declares regions.
benchmarkYesBenchmark slug, e.g. 'solana-rpc' or 'bridge-fee'. Get it from search_benchmarks.
providersYesTwo to ten provider names or slugs, as the user said them, e.g. ['Alchemy', 'Quicknode'].

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / providers / description
      Previous value: -"Two to ten provider names or slugs, as the user said them, e.g. ['Alchemy', 'QuickNode']."New value: +"Two to ten provider names or slugs, as the user said them, e.g. ['Alchemy', 'Quicknode']."
    • changedInput schema / properties / tier / description
      Previous value: -"Access cohort on chain RPC benchmarks: 'public' (default, free no-key endpoints) or 'keyed' (API-key providers such as Alchemy, QuickNode, Chainstack, GetBlock). Named providers usually live on the keyed cohort."New value: +"Access cohort on chain RPC benchmarks: 'public' (default, free no-key endpoints) or 'keyed' (API-key providers such as Alchemy, Quicknode, Chainstack, GetBlock). Named providers usually live on the keyed cohort."
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral detail beyond them: unmeasured providers land in `missing`, and providers below the ranking floor return rank null — with explicit instruction not to frame either as a loss. It stops short of describing overall result ordering or error behavior for an invalid benchmark slug.

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?

Front-loaded with the core action, then usage trigger, then prerequisite and edge-case handling — a logical order. The three quoted user phrasings are slightly more illustration than necessary, but they earn their place by disambiguating the trigger condition.

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 5-parameter tool with slicing (tier/chain/region) and no output schema, the description covers the primary return fields and the two tricky null/missing cases. It omits what an invalid benchmark slug produces and whether results come pre-sorted, which leaves minor gaps for an agent composing a response.

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%, including the tier cohort explanation and the 2-10 provider bounds, so the schema carries most of the burden. The description only adds the intent that providers are passed 'as the user said them' and reiterates the search_benchmarks dependency; 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?

A specific verb and resource: 'Puts two or more named providers side by side on one benchmark', plus the exact payload (rank, measured value, success rate). This makes it immediately distinguishable from sibling tools like recommend_provider (pick a provider) and get_benchmark (single benchmark detail).

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 trigger is given: 'Use when the user names the candidates themselves', reinforced with three concrete example utterances. It also names the prerequisite step ('Find the benchmark slug with search_benchmarks first') and how to treat unmeasured providers, so the agent knows both when to call it and how to proceed before and after.

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.