Skip to main content
Glama

Elucora Evidence API

Seal a hash you already hold

elucora_attest

Prove a piece of content existed at a point in time by sealing its SHA-256 hash. Use when you already hold the bytes — a model output, a tool result, a document. Elucora records that you submitted this hash and when; it does not prove where the content came from or that it is true, because Elucora never saw the source. To prove what a web source served, use elucora_capture instead. Consumes receipt quota.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hashYesSHA-256 digest of the content, written as sha256:<64 hex characters>.
metadataNoOptional signed scalar metadata.
size_bytesNoOptional size of the content, as described by the caller.
content_typeNoOptional media type of the content, as described by the caller.

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the sparse annotations, the description reveals that Elucora does not see or verify the source or truth, only that a hash was submitted at a time, and that it consumes receipt quota. This prevents false expectations.

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?

Very concise, with all sentences adding value: the usage condition, the limitation, the sibling alternative, and quota impact. Front-loaded with the core purpose.

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?

Covers purpose, usage, limitations, and quota, but does not explicitly state what the tool returns (e.g., a receipt ID, confirmation). Given no output schema, a brief return/confirmation statement would make it fully complete.

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 already describes all four parameters at 100% coverage, including the hash format and optional metadata fields. The description does not add new parameter-level details, so 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?

The description names a specific verb ('sealing its SHA-256 hash') and clear resource/action, and immediately distinguishes from sibling elucora_capture. This makes the tool's purpose unambiguous.

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?

Explicitly states when to use ('when you already hold the bytes') and directs users to elucora_capture for web source scenarios. It also notes quota consumption, which is relevant context.

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.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: attest for user-held bytes, capture for web sources, get_receipt for retrieval, and verify for validation. Descriptions explicitly cross-reference to avoid confusion.

Naming Consistency5/5

All tool names follow the elucora_ verb pattern (attest, capture, get_receipt, verify). The naming is consistent snake_case and predictable.

Tool Count5/5

Four tools is a well-scoped count for an evidence API: two creation variants, one retrieval, and one verification. No redundancy or bloat.

Completeness5/5

The tool set covers the full evidence lifecycle: creating proof (attest/capture), retrieving receipts, and verifying authenticity. Since evidence is immutable, update/delete are unnecessary.