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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds genuinely non-obvious behavior: invalid inputs are actively rejected rather than returning a null/sentinel, and each successful call costs $0.001 USDC via x402 on Solana. The HTTPS alternative endpoint is also useful operational context. It stops short of detailing the rejection format (error vs empty result).

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 core definition and the index convention lead, followed by validation rules, limits, and finally pricing/transport. Every sentence carries information, though the pricing/endpoint sentence is somewhat promotional and could be separated from the functional spec.

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 no output schema, the description correctly states that the return value is the smallest index n, and it covers the major edge cases (non-term values, leading zeros) and the input size ceiling. Behavior on rejection (error shape) and what n means for value 0 is only partially covered by the '0 is index 0' remark.

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 description coverage is 0%, so the description carries the full burden and mostly does: 'value' is a decimal integer of at most 600 digits, must be an actual Tribonacci term, and rejects leading zeros. The index-to-value mapping convention (0→index 0, 1→index 2) is also clarified. It could additionally note that value is passed as a string, but the semantics are well covered.

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 precise operation: return the smallest index n where the Tribonacci term equals the supplied value, plus the indexing convention (0 is index 0, 1 is index 2). A reader can distinguish it from term-producing siblings like tribonacci or trib_step, though it never explicitly names tribonacci as the companion tool and relies on the abbreviation 'T(n)' before clarifying with 'Tribonacci term' in the next sentence.

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 gives clear input preconditions (must be a Tribonacci term, no leading zeros, max 600 digits) which effectively tell the agent when the call will fail. But it never states when to prefer this over siblings such as tribonacci, trib_sum, or trib_mod, so tool selection is only implicitly inferable from the name and phrasing.

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