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

Without annotations, the description carries the full burden. It discloses that the output is from a lexicon and not AI-generated, and notes that Strong's numbers are provided only 'where known', indicating potential gaps. However, it does not explain behavior for invalid references, return format, or error handling, which would be important for a tool without any annotation support.

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?

The description is exceptionally concise—two sentences with no fluff. The key purpose and data source are front-loaded, and the example directly clarifies the sole parameter. The emphasis on 'FOUND' is stylistic but doesn't detract from clarity.

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?

For a simple one-parameter tool with no output schema, the description is nearly complete: it states purpose, source, a parameter example, and a data-quality caveat. It could mention what the return payload looks like or how to handle unknown references, but these are lower priority given the tool's simplicity and limited scope.

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 0%, so the description must clarify the 'ref' parameter. It does so by explaining that 'ref' is a Bible reference and supplying the example 'John 3:16', which adds meaning beyond the bare string type. While it doesn't list accepted reference formats, the example is sufficient for most use cases.

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?

The description clearly states what the tool does: returns the original-language (Hebrew/Greek) words behind a verse, with Strong's numbers where known. It distinguishes itself from siblings like word_occurrences and word_study by emphasizing its lexical source ('FOUND in the lexicon, never generated') and by giving a concrete example ('John 3:16').

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?

The description implies usage by explaining the input format ('Pass ref') and providing an example, but it lacks explicit when-to-use guidance or references to alternatives. The phrase 'never generated' hints at choosing this tool for authoritative data, but no outright exclusions or comparisons to sibling tools are given.

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