Skip to main content
Glama

Verify a fact package

fact_package_verify
Read-onlyIdempotent

Verify a fact package from fact_package_create: recompute every fact's hash, the Merkle root and the digest from the content (any changed fact, title, date or document list shows as a mismatch); check each fact against fact_validate; check the Ed25519 signature, against the public_key you pass (base64url, the signer's key you trust) or, without one, only against the key inside the package (which proves nothing about who signed); and, given the source documents' pages, check every quote is on its cited page. Returns valid plus each check's details, checks_run and checks_not_run (what was and was not checked), and values_not_checked: the parts of extracted facts' values that their quotes do not confirm (a true/false value, an enum, a summary), which do not change valid. Not checked: that the pages you pass are the original files (pass sha256 to tie them to the file hash), or what the facts mean.

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": {
      "package": "<package>"
    },
    "name": "fact_package_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
packageYesA fact package from fact_package_create, signed or not.
documentsNoOptional: the source documents' pages (with sha256 when the facts cite the file's hash). Each fact's quote is then checked on its cited page.
public_keyNoThe signer's Ed25519 public key you trust: 32 bytes as base64url (a JWK's x). With it the signature must verify for the package to be valid.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: any changed fact/title/date/document shows as a mismatch, unsigned verification "proves nothing about who signed," values_not_checked does not affect valid, and pages are not proven to be the original files. This exceeds what the annotations convey.

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?

Dense but every clause adds information; the verification steps, return fields, and explicit non-checks are front-loaded. The single semicolon-chained paragraph is harder to scan than a short list would be, which costs a point.

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 complex tool with nested objects and no output schema, the description names the return shape (valid, per-check details, checks_run, checks_not_run, values_not_checked) and explicitly bounds what is not verified. An agent has enough to invoke it correctly and interpret the result.

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 baseline 3 applies, but the description adds real semantics not obvious from the schema: the trust distinction for public_key (trusted signer key vs. the package's own key) and the conditional role of documents/sha256 in tying pages to a file hash. It stops short of detailing the pages array indexing, which the schema already covers.

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?

Opens with a specific verb and resource ("Verify a fact package from fact_package_create") and enumerates exactly what is recomputed: fact hashes, Merkle root, digest, signature, and page-level quotes. It is clearly distinguishable from fact_package_create (which produces) and fact_validate (which it invokes per fact).

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 clear conditional guidance: pass public_key when you have a trusted signer key, otherwise the signature check only proves internal consistency; pass documents when you want quote-on-page checks. It does not explicitly say when to prefer this over sibling doc_verify_facts or doc_verify_claim, which is the remaining gap.

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.