Skip to main content
Glama

check_document

Read-onlyIdempotent

A whole document in one call: the claims that can be verified against a primary source, each answered by the door that owns it with its own signed receipt, plus one receipt over the document. Extraction is mechanical, so the claim list and the count are reproducible from your document alone — nothing is inferred. This rail answers the first 5 claims for a flat US$0.25 (5 cents a claim); a better-funded document goes to the pack-funded HTTP door (POST /document, up to 25 claims at the same 5 cents a claim), whose included preview lists the claims and the price before anything is charged — use it first if you are unsure the document holds anything checkable. This door reads PROSE: to check a bare list of references or package versions, use verify_bulk, and a single claim belongs to check_figure, check_entity, verify_citation or verify_package. Comes with an Ed25519-signed receipt covering the question, the verdict, the sources and the time, checkable offline against the published key at /.well-known/factstamp-issuer.json — so the check itself can be audited later by someone who was not here.

Input Schema

NameRequiredDescriptionDefault
documentYesThe document text. Only sentences that name something we cover AND carry the value to check become claims; everything else is reported as considered.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, and the description adds substantial non-annotated behavior: mechanical reproducible extraction, no inference, pricing and claim cap, preview-before-charge behavior for the pack door, and an offline-auditable Ed25519-signed receipt. No contradiction with annotations.

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-loads the core operation with "A whole document in one call" and then groups pricing, alternatives, and receipt details. It is dense and repeats the receipt concept somewhat, but most detail is justified by pricing, auditability, and routing complexity.

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?

Without an output schema, the description still explains the return shape enough: per-claim answers from owning doors with signed receipts plus one document-level receipt. It also covers cost, alternatives, and offline verification, which is complete for a one-parameter verification tool.

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 `document` parameter is already well documented. The description adds that this door expects PROSE rather than a bare list, which helps content selection, though that point also overlaps with usage guidance.

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 a whole document for verifiable claims and returns per-claim and document receipts. It explicitly distinguishes itself from verify_bulk and single-claim siblings like check_figure, check_entity, verify_citation, and verify_package.

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?

Gives explicit when-to-use guidance: prose documents up to 5 claims for US$0.25, with a pack-funded HTTP door for better-funded or uncertain cases. It also names alternatives for bare lists and single claims, so the agent can route correctly.

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.