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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, so the safety profile is given. The description does add genuine behavioral context beyond that: Tamil/English lexical matching with no guarantee for other languages, the exact returned field set, the additive-lens usage rules, and that a conflicting query/kural_id fails rather than silently substituting. Rich disclosure, but omits anything about result size limits or how ranking works when no kural_id is supplied.

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?

Front-loads the "CALL FIRST" directive and the trigger list before any mechanics, which is the right order. The back half compresses several distinct rules (citation discipline, format choice, kural_id precedence, locale basis, opt-in originals) into a dense run of clauses that is harder to parse than it needs to be.

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 6-parameter, read-only retrieval tool with an output schema and full schema coverage, everything an agent needs is present: trigger conditions, query phrasing, format selection, citation rules, language limits, and conflict behavior. No material gap remains.

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?

With 100% schema coverage the baseline is 3; the description earns a bump by telling the agent to pass the situation in natural language, recommending response_format:compact for normal answers while noting full preserves legacy fields, and explaining that an explicit kural_id bypasses topic ranking. It stops short of explaining limit interplay or how locale auto-detection behaves for mixed-language queries.

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 (retrieve/ground) and resource (a verified Thirukkural couplet) plus the exact triggering domain (personal, emotional, moral, family, life-guidance). The "CALL FIRST" framing positions it against any other tool, and the enumerated return fields leave no ambiguity about what comes back.

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?

Gives explicit when-to-use conditions with concrete user phrasings and clarifies that the user need not mention the Thirukkural. However, it never names the sibling verify_quote or states when to prefer it, so the division of labor between retrieval and verification is only hinted at ("never invent quotations").

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