Transliterate text between Indic scripts and Latin. Source/target script names: Devanagari, Bengali, Tamil, Telugu, Kannada, Malayalam, Gurmukhi, Gujarati, Oriya, Latin (also accepts ISO 15919 / IAST as Latin variants in the private extended build). Fast common-word path; falls back to Aksharamukha for full coverage.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| to_script | Yes | Target script name. | |
| from_script | Yes | Source script name. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses performance behavior (fast path, fallback) and acceptable script variants (ISO 15919/IAST). No destructive behavior is expected, and the description adds value beyond the tool's name.
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 sentences front-load the essential information: purpose, script list, and performance characteristics. Every sentence adds value without redundancy.
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 tool with 3 parameters and no output schema, the description adequately covers purpose, scripts, and behavior. Return format is implied but not explicitly stated; however, the tool is simple enough that this is not a major gap.
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 provides descriptions for to_script and from_script but not text (67% coverage). The description adds meaning by listing accepted script names and explaining fallback behavior, compensating for the missing schema description of text param.
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 the tool's purpose: transliterating text between Indic scripts and Latin. It enumerates specific script names (Devanagari, Bengali, etc.), providing precise scope. It distinguishes from sibling tools like detect_script and normalize_name by focusing on transliteration.
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 mentions a 'fast common-word path' and fallback to 'Aksharamukha for full coverage', giving performance context. However, it does not explicitly state when or when not to use this tool versus alternatives like detect_script. Sibling tools are different enough that usage is clear.
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.
The tools cover distinct tasks: script detection, identifier validation, address/name normalization, and transliteration. Some overlap exists (e.g., PIN codes appear in both pincode_to_locality and normalize_address), but descriptions clarify each tool's role.
All names use snake_case, but the pattern varies: detect_script, normalize_address, and normalize_name are verb_noun, while gstin_info, pincode_to_locality, and state_from_pan are noun_verb. transliterate is just a verb, breaking the pattern.
With 7 tools, the count is well within the ideal range (3-15) and appropriately covers the server's domain of Indian text and identifier processing without being excessive.
The toolset covers core functionality: script detection, address/name normalization, PIN and PAN/GSTIN extraction, and transliteration. Missing operations like Aadhaar validation or bulk processing are minor given the stated purpose.