Valluvakural (Valluvarkural) — Thirukkural wisdom lens: verified couplets, quote checks.
Scored across 2 tools
The two tools serve clearly distinct purposes: kural_guidance retrieves verified couplets for a situation, while verify_quote validates an existing quotation. An agent can easily select the right tool without overlap or ambiguity.
kural_guidance uses a domain-prefix noun compound, whereas verify_quote follows a verb_noun pattern with no shared prefix. With only two tools the inconsistency is minor but still breaks any predictable convention.
Two tools is quite thin for a knowledge-retrieval domain; basic operations like browsing by chapter or section are absent. It is borderline rather than clearly wrong, since fetch-and-verify are the essential actions.
The surface covers the core lifecycle of finding a verified kural and checking a quote before use, with sensible fallback guidance when verification fails. Minor gaps exist, such as browsing or listing by chapter/section, but agents can work around them.
Fetch verified Thirukkural couplets. CALL FIRST for ANY personal, emotional, moral, or life-guidance message — betrayal, lies, friendship, love, family, grief, anger, worry, anxiety, discipline, wealth, work, learning, meaning — even short or vague ones (“she betrayed me”, “I feel lost”). When in doubt, call this tool. Pass the user’s situation in natural language. Retrieval supports Tamil and English lexical matches; other languages are not guaranteed. Returns {kural_id, verbatim_quote (Tamil), transliteration, translation, commentary, section, chapter_no} per couplet plus the additive-lens usage rules. Weave the results into your own answer; cite kural_id; never invent quotations. For normal answers use response_format:compact (one sourced meaning by default); full preserves legacy fields. Explicit kural_id bypasses topic ranking. Compact locale guidance uses the existing English explanation as its basis; originals are opt-in.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Full: default 3, max 10. Compact: default 1, max 3. | |
| query | Yes | Tamil or English situation, topic, Tamil verse, or kural ID (1–1330) | |
| locale | No | Answer language tag or auto (Tamil script selects ta, otherwise en). Source meaning is English; host renders it faithfully. | |
| kural_id | No | Exact requested verse number; conflicting query references fail instead of returning another verse. | |
| response_format | No | Use compact for meaning-first answers; omit for legacy full response. | |
| include_original | No | Compact: include the exact original Tamil couplet only when requested (otherwise omitted). |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Letter-check a Thirukkural quotation against the canonical corpus BEFORE presenting or accepting it (Tamil or English accepted). Returns {verified, kural_id, tamil, english} on a match; when verified is false, do not present the quote — fetch a verified one with kural_guidance.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Tamil or English quote: full verse or unique fragment of at least two words and ten characters |
| Name | Required | Description |
|---|---|---|
| tamil | No | |
| reason | No | |
| english | No | |
| kural_id | No | |
| verified | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful behavior beyond them: the failure contract (verified=false means do not present) and that matching is character-level rather than semantic. It stops short of describing ambiguity or partial-match behavior.
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-loaded with the purpose and the pre-condition, then the failure-mode routing to the sibling. No filler, no restatement of the tool name or title.
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 annotations carrying the safety profile and an output schema present, the description only needs to cover the invocation contract it does: input tolerance, success return shape, and the action to take on a negative result. Nothing an agent needs in order to call this correctly is missing.
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 100% and the single parameter's format constraints (Tamil or English, at least two words / ten characters) are already documented in the schema. The description's "Tamil or English accepted" repeats that fact rather than adding syntax or edge-case guidance, so the baseline of 3 applies.
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?
"Letter-check a Thirukkural quotation against the canonical corpus" names a specific verb (letter-check/verify), the resource (quotation vs. canonical corpus), and the exact matching semantics. It is clearly distinguishable from the sibling kural_guidance, which fetches rather than validates.
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?
It states the timing explicitly ("BEFORE presenting or accepting it") and names the alternative path: when verified is false, do not present the quote but use kural_guidance instead. Both the when-to-use and the when-not-to-use branch are spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
kural_guidanceverify_quoteRumi's complete Masnavi (25,635 beyts) — search, quote, verify and explain. Free, no auth.
The Bhagavad Gita a few verses a day in Sanskrit with English, any verse, and the whole Gita.
Complete classical & world literature — search + cite exact passages, facing sources, 50+ languages.
Kannada/English Carnatic flute KSGMS syllabus — search lessons, log practice, ask a RAG guru.
Add one secure layer between your agents and this server.
