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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), so the bar is lower, and the description adds genuinely new context: per-call pricing (0.005 USDC, included in subscriptions) and the enumerated verdict values with reasons. It does not explain latency, freshness of "our history," or failure behavior for unknown mints.

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 signal list, and the pricing sentence is short and useful. The opening is dense with a comma-heavy list but nothing is redundant or padding.

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 must convey return content, and it does: the four risk signals plus the verdict enum values and "with reasons." It omits how thresholds map to verdicts and what happens on unsupported tokens, but an agent has enough to invoke and interpret it.

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 75%, with mint, quote, and amount already documented in the schema, so the schema carries most of the load. The description adds no parameter-level detail — it never restates that quote defaults to SOL or clarifies buy-vs-sell unit conventions — so the baseline 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?

The description names a specific operation (pre-swap safety preflight on Solana) and enumerates the exact signals returned: price impact, sandwich share, Token-2022 transfer fees/hooks, freeze authority, and a verdict. This clearly separates it from siblings like token_deep_check or pool_health, which do not bundle a swap verdict.

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?

"Before a Solana swap" gives a clear, explicit trigger condition for when to call it. However, it never names an alternative tool or states when not to use this one (e.g., for non-swap token safety, use token_deep_check), so the routing guidance stops short of full coverage.

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