Skip to main content
Glama

Verify card citations

verify_citations
Read-onlyIdempotent

Checks up to 20 BrainVault card refs (v3:N) at once, for citing cards in answers. For each ref: exists, public (text readable), sha256_ok (on-chain text matches its fingerprint), creator (minting address) and official (minted by a Wave signer). Read-only, free, no key. Use card_read to get a card's text.

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": {
      "refs": "<refs>"
    },
    "name": "verify_citations"
  }
}

Input Schema

NameRequiredDescriptionDefault
refsYesUp to 20 card refs like v3:142, as a list (or one comma-separated string)

Output Schema

NameRequiredDescriptionDefault
blockNo
staleNo
sourceNo
resultsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / refs / description
      Previous value: -"v3:N refs (or a comma list)"New value: +"Up to 20 card refs like v3:142, as a list (or one comma-separated string)"
    • addedInput schema / properties / refs / minItems
      Added value: +1
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "properties": {
      +    "block": {
      +      "type": [
      +        "integer",
      +        "null"
      +      ]
      +    },
      +    "results": {
      +      "items": {
      +        "properties": {
      +          "creator": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "exists": {
      +            "type": "boolean"
      +          },
      +          "official": {
      +            "type": "boolean"
      +          },
      +          "public": {
      +            "type": "boolean"
      +          },
      +          "ref": {
      +            "type": "string"
      +          },
      +          "sha256_ok": {
      +            "type": [
      +              "boolean",
      +              "null"
      +            ]
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "source": {
      +      "type": "string"
      +    },
      +    "stale": {
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world. The description still adds non-obvious operational context: it is free and requires no API key, and it discloses exactly which per-ref predicates are evaluated, including on-chain fingerprint matching and Wave-signer provenance. It does not mention the behavior for invalid or non-existent ref formats, which is the main remaining gap.

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, front-loaded with the verb and scope, then the per-ref return fields, then the alternative tool. No filler and no repetition beyond a minor overlap on the 20-item cap.

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?

An output schema exists, so return values needn't be explained, yet the description still enumerates the checked fields to orient the agent. For a single-parameter, read-only tool this covers everything an agent needs to call it correctly; only edge-case behavior for malformed refs is absent.

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 coverage is 100% and the schema already documents the v3:142 format, the maxItems of 20, and the comma-separated-string alternative. The description's 'up to 20 ... (v3:N)' largely restates that. Baseline 3 applies since the schema carries the parameter burden.

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 ('Checks ... BrainVault card refs') plus the batch capacity (up to 20) and the intended use case ('for citing cards in answers'). The per-ref checklist (exists, public, sha256_ok, creator, official) makes the exact output semantics unambiguous without opening the 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 a clear situational trigger (verifying citations used in answers) and explicitly routes the agent elsewhere for the complementary task: 'Use card_read to get a card's text.' Doesn't state when verification is unnecessary or what to do about failed refs, so it stops short of full when/when-not coverage.

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