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

Annotations already establish readOnlyHint=true, and the description reinforces this with 'Nothing is signed or sent.' It adds genuinely useful behavior beyond the annotations by defining the three-outcome verdict model and noting reasons are returned, though it omits what happens on error or how long the checks take.

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?

Three tight sentences: when to call it, what it does, what it returns, then a scope disclaimer. The verdict vocabulary is front-loaded where an agent needs it, and no sentence is 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?

For a four-parameter, no-output-schema tool, the description covers purpose, safety posture, and return shape well enough to invoke correctly. It leaves a small gap on failure behavior and the relationship to the sibling single-purpose checks.

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%, so mint, intent, exclude, and transaction are all documented in the schema itself. The description only gestures at the token and the about-to-be-signed transaction and says nothing about the 'exclude' holder-filter parameter, so it adds little beyond structured data.

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 composite action: rug-check the token plus Presign Guard review of the unsigned buy transaction, returning a single green/orange/red verdict. It clearly distinguishes itself from the separate rugcheck and presign_check siblings by naming both capabilities in one call.

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 trigger condition is explicit and front-loaded: 'Before a bot buys a Solana token.' It implies this replaces calling rugcheck and presign_check separately, but never states that trade-off or when a single-purpose sibling would be preferable.

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