Skip to main content
Glama

Besorah — the Bible in Hebrew, Greek, Aramaic and English

Compare the texts of a verse

compare_witnesses
Read-onlyIdempotent

Returns one verse across the texts side by side: Hebrew, the Septuagint (matched by the app's verse tables, even where numbered differently), the Targumim, and the Greek and Hebrew New Testament, with the quotations that join them and the Greek words a New Testament quotation and the Septuagint do and do not share. Use when the user asks how one verse reads in the Hebrew, Septuagint, Targum and New Testament.

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": {
      "reference": "<reference>"
    },
    "name": "compare_witnesses"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNooptional: json (default) or markdown (compact, readable)
max_charsNooptional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
referenceYese.g. 'John 3:16', 'Psalm 23', 'Genesis 1:1-3'

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already establish the safe-read profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real behavior: the Septuagint is 'matched by the app's verse tables, even where numbered differently,' which pre-empts a common confusion about versification mismatches. It also discloses the shape of what comes back (side-by-side texts, linking quotations, shared/divergent Greek words), which matters since there is no output schema. It does not mention failure modes, e.g. what happens for a verse absent from the Targum.

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?

Two sentences, front-loaded with what is returned before the usage cue, and every clause carries information. The first sentence is long and heavily nested with parentheticals and a multi-item list, which slightly hurts scannability but is not padding.

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?

With no output schema, the description carries the burden of telling the agent what comes back, and it does so with a concrete inventory of texts, quotations, and shared vocabulary; the annotations cover the safety profile. Gaps are minor: no statement about coverage limits (e.g. verses with no Targum or no LXX witness) or how the default JSON differs from markdown beyond the schema's own note.

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 description coverage is 100%, so the schema already documents reference, format, and max_chars, and the baseline of 3 applies. The only added meaning is indirect: the note about verse-table matching and differing numbering implies the reference parameter tolerates versification differences, but nothing is said about format or truncation behavior beyond the schema text.

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 concrete verb and resource ('Returns one verse across the texts side by side') and then enumerates exactly which witnesses are included: Hebrew, Septuagint, Targumim, and Greek/Hebrew New Testament, plus the joining quotations and shared/non-shared Greek vocabulary. That enumeration is what separates it from generic siblings like get_passage or get_verse_study, so an agent can pick it 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?

It gives an explicit trigger: 'Use when the user asks how one verse reads in the Hebrew, Septuagint, Targum and New Testament.' That is a clear usage condition, but no when-not condition and no named alternative (e.g. get_verse_study) for users who want commentary rather than a text comparison.

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