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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), but the description adds real behavioral content beyond them: the exact return shape on a match and the required agent action on a mismatch. It stops short of covering edge cases like near-miss or ambiguous fragments, which keeps it from a 5.

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, both load-bearing, with the imperative precondition front-loaded and the failure-path instruction second. No restatement of the title or filler.

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?

An output schema exists, so the return-field enumeration is a bonus rather than a necessity, and the critical thing an agent could get wrong — presenting an unverified quote — is explicitly forbidden. Nothing needed to invoke it 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 is fully documented there, including the two-word/ten-character fragment minimum. The description's only added note ("Tamil or English accepted") duplicates the schema, so this rests at the baseline.

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 (letter-checks) and resource (a Thirukkural quotation) against a named authority (the canonical corpus), and names the sibling tool kural_guidance as the fallback path. An agent can distinguish it from kural_guidance without opening either 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?

Gives an explicit trigger ("CALL THIS BEFORE QUOTING any Thirukkural verse") and an explicit negative branch ("when verified is false, do not present the quote — fetch a verified one with kural_guidance"). Both the when and the when-not, plus the named alternative, are stated outright.

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