[WORD · door] Read a passage — a single verse, a range (John 3:16-18), or a whole chapter (John 3). The WEB by default; lang picks a held public-domain translation (es, fr, de, zh, he, la, ru, ar, ja, ko, …; an unknown lang lists what is held).
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | ||
| lang | No | ISO 639-1, default en |
Changes observed during successful MCP inspections.
Input schema / properties / langAdded value: +{
+ "description": "ISO 639-1, default en",
+ "maxLength": 4000,
+ "type": "string"
+}Input schema / additionalPropertiesAdded value: +falseInput schema / properties / ref / maxLengthAdded value: +4000Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden, and it does disclose meaningful behavior: default translation is WEB, lang selects a held public-domain translation, and an unknown lang enumerates what is available rather than silently failing. It doesn't state read-only safety or error behavior, but those are largely self-evident for a 'read' tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two dense, front-loaded sentences with no filler; the ref-format detail comes before the translation detail. The leading bracket tag '[WORD · door]' is cryptic but the payload is terse and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description should ideally indicate what is returned (passage text, reference header, etc.), and it does not. Parameter behavior is well covered, but return-shape completeness is a clear gap for a retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 50% (ref has no schema description), and the description compensates well — it defines the accepted ref formats with examples and explains lang semantics (default WEB, fallback behavior for unknown values), adding real meaning beyond the schema's bare 'ISO 639-1, default en'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Read') and resource ('a passage') and immediately bounds the scope with three concrete examples — single verse, range (John 3:16-18), whole chapter (John 3). This lets an agent tell it apart from siblings like 'search', 'lookup', or 'commentary' 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by the scope description (read text by reference), but there is no explicit when-to-use guidance or named alternative. The agent must infer that this is the tool for direct scripture retrieval versus search/commentary tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.