Skip to main content
Glama

check_analyze

Idempotent

Spends ONE paid credit on the networks it paid: evmWallet on the EVM networks paid, solanaWallet on Solana if it was paid. Give a wallet for each family the credit paid (check_wallet_missing otherwise) and none for a family it did not (check_family_not_paid). The free screening (OFAC SDN, issuer freeze) and Scorechain read each wallet once, Merkle Science (through Didit) once per network, at most the networks paid plus 2 lookups in all. Returns check with status used, target { wallets { evm, svm }, networks }, seal (the worst network: red, risk found; yellow, medium risk; grey, a paid reading did not come back; green, no risk, Merkle no_data included), result and screening (of the worst network), networks [{ chainId, seal, result { verdict, risk, tools [{ tool, result clear|flagged|unavailable, score 0-100, severity, summary, category, factors, sourceOfFunds, destinationOfFunds, analyzedAt, fromHistory }], details }, screening }] and events (the real steps, with ms). The same credit and the same wallets again answers what is stored, with no provider call; other wallets are check_credit_used (409). Two calls at once run ONE analysis (the other gets check_running, 409). check_unreadable (503): a reading did not answer, the credit is still valid, call again with the same arguments (details.missing names tool:network). analysis_tool_unavailable (503): a tool is down and the credit was not touched. The credit is per tool (independent review of 18/11/2026): a paid tool that cannot read now (crystal with the payer's KYC no longer approved, a tool Vurto switched off) is NOT spent: the others read, the result shows only them, and the answer carries pendingTools [{ tool, reason kyc_required|switched_off }] and pendingCheckId, a credit of its own for the pending tools bound to the same wallets (keep it like any Check id; call check_analyze with it later). With no paid tool able to read, check_tools_pending (409, details.pending) and nothing is spent.

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": {
      "checkId": "<checkId>"
    },
    "name": "check_analyze"
  }
}

Input Schema

NameRequiredDescriptionDefault
walletNoInstead of the two above, for a credit of one family: the wallet, its family read from the address.
checkIdYesThe Check id from check_charge (CHK-...). It is the capability of this Check: keep it, and keep it private.
evmWalletNoThe EVM wallet to analyse (0x...), when the credit paid an EVM network.
solanaWalletNoThe Solana wallet to analyse (base58, case-sensitive), when the credit paid Solana.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • removedInput schema / properties / access
      Removed value: -{
      -  "description": "The Check access of this payer from check_access (vca_...). Secret: it reads and spends this payer's credits.",
      -  "type": "string"
      -}
    • removedInput schema / properties / chainId
      Removed value: -{
      -  "description": "EVM: integer from GET /v1/chains (1, 10, 56, 100, 137, 8453, 42161, 43114, 130). Solana: string from GET /v1/svm/chains (\"solana-mainnet\").",
      -  "type": [
      -    "integer",
      -    "string"
      -  ]
      -}
    • changedInput schema / properties / checkId / description
      Previous value: -"A paid check id (check_credits lists them)."New value: +"The Check id from check_charge (CHK-...). It is the capability of this Check: keep it, and keep it private."
    • addedInput schema / properties / evmWallet
      Added value: +{
      +  "description": "The EVM wallet to analyse (0x...), when the credit paid an EVM network.",
      +  "type": "string"
      +}
    • removedInput schema / properties / payer
      Removed value: -{
      -  "description": "The wallet that paid this Check.",
      -  "type": "string"
      -}
    • addedInput schema / properties / solanaWallet
      Added value: +{
      +  "description": "The Solana wallet to analyse (base58, case-sensitive), when the credit paid Solana.",
      +  "type": "string"
      +}
    • changedInput schema / properties / wallet / description
      Previous value: -"The wallet to analyse (0x on EVM, base58 on Solana, case-sensitive)."New value: +"Instead of the two above, for a credit of one family: the wallet, its family read from the address."
    • changedInput schema / required
      Previous value: -[
      -  "checkId",
      -  "wallet",
      -  "chainId",
      -  "payer",
      -  "access"
      -]New value: +[
      +  "checkId"
      +]
  2. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only give readOnlyHint=false and idempotentHint=true; the description goes far beyond by naming the credit cost, the idempotent replay rule, the single-flight concurrency behavior, the per-network lookup cap ('networks paid plus 2'), and the full failure taxonomy with statuses (503 check_unreadable, analysis_tool_unavailable, 409 credit_used/running/tools_pending). It also discloses the pendingTools/pendingCheckId partial-credit path and that a tool down does not consume the credit. Nothing here contradicts the annotations.

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

Conciseness2/5

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

The core action is front-loaded, but the text is a dense run-on stream mixing return shape, error codes, KYC edge cases and vendor names in single sentences with no paragraphs or lists. Much of the error-code detail could be segmented or deferred, and the wall-of-text format makes it hard to scan despite most sentences carrying operational information.

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?

For a tool with no output schema, no enums and high behavioral complexity (multi-chain credit, provider outages, partial pending credits), the description covers inputs, the returned structure (check, target, seal, result, screening, networks, events), and the failure semantics needed to recover. An agent has enough to invoke it and interpret both success and error responses.

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?

Schema coverage is 100%, so the baseline is 3, and the description earns above that by explaining relationships the schema cannot: which wallet params to supply based on which families the credit paid, that 'wallet' is an alternative for one-family credits with the family derived from the address, and that checkId is the capability token of the credit and should be kept private. It does not add format/syntax detail, but the semantic constraints it adds are material.

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 opening sentence states the operation concretely: it spends one paid credit to analyse the wallets across the network families that credit covers, and the return sentence names the resource (check with status used, wallets, networks, seal, result). It is specific about verb and scope but relies on heavy domain jargon ('credit', 'seal', 'paid networks') and never states the action in one plain sentence, so an agent must read several clauses to confirm it is an analysis call.

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?

It routes the agent explicitly: supply a wallet for each family paid and none for an unpaid family, otherwise expect check_wallet_missing / check_family_not_paid. It states when re-calling is safe (same credit and wallets returns stored data with no provider call), that other wallets resolve to check_credit_used (409), concurrent calls yield check_running (409), and that no readable paid tool yields check_tools_pending (409). This is near-complete when-to-use/when-not guidance with named alternatives.

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