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

Find words by grammar

query_words

Read-onlyIdempotent

Finds every word by grammar and/or Strong's number, within a book or testament — e.g. all Qal imperatives of H1285 in the Prophets, every aorist passive participle in Paul, every Hiphil verb in Isaiah. grammar takes the words of the parsing (Qal, Hiphil, imperative, participle, feminine, plural, aorist, passive, genitive, 3rd…); all must be on the same word. Hebrew by default for H ids and Tanakh books, Greek for G ids and the New Testament; edition=septuagint for the Septuagint. Returns the matching words with their verses and a count per book, 10 per page by default (limit 1-25, and nextOffset continues). Use when the user asks for words by grammatical form, such as every Qal imperative or aorist passive participle.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "query_words"
  }
}

Input Schema

Name	Required	Description
`book`	No	restrict to one book, e.g. Isaiah
`limit`	No	how many results to return (1-25, default 10)
`format`	No	optional: json (default) or markdown (compact, readable)
`offset`	No	how many results to skip; the previous answer's nextOffset is where its page ended
`edition`	No	hebrew \| greek \| septuagint
`grammar`	No	e.g. 'Qal imperative', 'aorist passive participle', 'feminine plural'
`strongs`	No	e.g. H1285 (optional)
`max_chars`	No	optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
`testament`	No	tanakh \| new testament \| apocrypha

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 12, 2026

changedInput schema / properties / limit / description

Previous value: -"how many to return"New value: +"how many results to return (1-25, default 10)"

Changed2 schema fields changedNov 12, 2026

addedInput schema / properties / book / description

Added value: +"restrict to one book, e.g. Isaiah"

addedInput schema / properties / offset / description

Added value: +"how many results to skip; the previous answer's nextOffset is where its page ended"

First observedNov 11, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent/closed-world, yet the description still adds substantial behavior: automatic language inference (H ids and Tanakh books → Hebrew, G ids and New Testament → Greek), the edition=septuagint switch, the return shape (matching words with verses and a per-book count), default page size of 10, the limit 1-25 range, and how nextOffset continues paging. This is exactly the kind of context that a count-based, paginated query tool needs beyond its safety hints.

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?

The purpose and examples come first, then semantics, then return/pagination behavior, then usage routing — a sound front-loaded order. The middle sentence is dense with semicolon-separated clauses and could be split, but almost no wording is redundant.

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 9-parameter, all-optional query tool with no output schema, the description supplies what the structured fields cannot: language defaults, edition override, result shape with per-book counts, page size and continuation. An agent could call and paginate this tool correctly from the description alone.

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 a 3 is the floor, but the description goes further: it explains that grammar takes individual parsing tokens and that 'all must be on the same word' — a constraint the schema does not express — and it clarifies the interdependence of offset and the returned nextOffset. It does not fully restate every parameter (max_chars, format), relying on the schema for those.

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 ('Finds every word by grammar and/or Strong's number') plus the scoping dimension ('within a book or testament'), then cements it with three concrete examples of grammatical queries. An agent can distinguish this lexical/grammatical retrieval from text search without opening the sibling schemas.

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?

Ends with explicit routing guidance: 'Use when the user asks for words by grammatical form, such as every Qal imperative or aorist passive participle.' That is a clear use condition, but it names no alternative (e.g. search_words) and gives no when-not or fallback case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Besorah — the Bible in Hebrew, Greek, Aramaic and English tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?