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

Annotations already cover read-only, idempotent, non-destructive and open-world semantics, so the description's real contribution is the non-obvious commercial context: $0.001 USDC per successful call via x402 on Solana, with an alternate HTTPS endpoint. That paid-call disclosure is exactly the kind of behavior an agent needs and cannot get from structured fields; only the response format detail (comma-separated string) is left implicit.

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?

It is front-loaded with the output definition, then an example, then parameter bounds, then pricing and the alternate endpoint. Every sentence carries information; the only redundancy is restating the min/max bounds that the schema already enforces.

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 two-parameter pure computation with no output schema, the description supplies the output shape (comma-separated, survivor omitted), a concrete verification example, valid input ranges, and the payment/transport details. Nothing critical is missing for correct invocation, though a note distinguishing it from josephus_first or josephus_place would close the last 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 description coverage is 0%, so the description carries the burden, and it partially does: 'With 5 people and every 2nd' implicitly defines n as the circle size and k as the step, and it restates both bounds. However, it never explicitly labels n and k, so the mapping has to be reverse-engineered from the example rather than read directly.

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 names the exact resource (the elimination order of the Josephus circle) and its output form, and explicitly scopes it as excluding the survivor, which is a meaningful distinction among the josephus_* family. It stops short of naming the close siblings (josephus, josephus_first, josephus_k2, josephus_place), so an agent must infer the split from the 'not including the survivor' clause alone.

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?

There is no explicit statement of when to use this tool versus josephus or josephus_first, even though four closely related siblings exist in the list. The worked example implies the intent but gives no routing rule or exclusion, leaving sibling selection entirely to inference.

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