Skip to main content
Glama
Sign In

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

by bible.besorah
OverviewDiscussionsAdmin

Words that keep company

get_collocations
Read-onlyIdempotent

Returns the words that keep company with a Hebrew or Greek word: those that appear in the same verse more often than chance predicts (log-likelihood), strongest first, 15 by default (limit 1-25). Pass strongs (H430) or a word ('shepherd'). Pass with=<Strong's id> to read the verses where two words meet. corpus: he, nt or lxx. Use when the user asks which words commonly appear alongside a given Hebrew or Greek word.

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": {
      "strongs": "<strongs>"
    },
    "name": "get_collocations"
  }
}

Input Schema

NameRequiredDescriptionDefault
withNoa second Strong's id, to see the verses with both
limitNohow many results to return (1-25, default 15)
corpusNohe (Hebrew Bible), nt (Greek New Testament) or lxx (Septuagint)
formatNooptional: json (default) or markdown (compact, readable)
strongsYesH430, or an English/transliterated word
max_charsNooptional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"how many to return"New value: +"how many results to return (1-25, default 15)"
  2. Changed1 schema field changed
    • addedInput schema / properties / corpus / description
      Added value: +"he (Hebrew Bible), nt (Greek New Testament) or lxx (Septuagint)"
  3. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds the ranking basis (log-likelihood, strongest first) and the default of 15 results, which is real behavioral context beyond the annotations. It does not describe result shape or what happens when a word is ambiguous across corpora.

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 output definition and ranking, then packs usage into a final sentence; nearly every clause earns its place. It is dense with parentheticals and slightly run-on, which costs a point on readability.

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?

No output schema, yet the description tells the agent what is returned (ranked word list), ordering, default size and range, and the alternate verse-listing mode. Combined with annotations covering safety, an agent has enough to call it correctly; only edge cases (ambiguous word input, empty results) are unaddressed.

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 coverage is 100%, so baseline is 3. The description does add value for 'with' (it turns the tool into a verse listing rather than a collocation list) and restates the strongs/word and corpus options. The limit, format and max_chars semantics come entirely from the schema.

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 ('Returns the words that keep company with a Hebrew or Greek word') and pins down the metric (same-verse co-occurrence, log-likelihood ranking), which distinguishes it from sibling word tools like get_word_occurrences. An agent can tell what it produces 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?

Ends with an explicit trigger: 'Use when the user asks which words commonly appear alongside a given Hebrew or Greek word.' It also explains the alternative mode ('Pass with=... to read the verses where two words meet'), steering the agent between co-occurrence listing and verse retrieval. No explicit when-not or named sibling routing, so not a 5.

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 toolsInspect
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