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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavior: it returns a 0-100 score, totals SOL locked in empty token accounts, and returns a remediation link for the owner — none of which the annotations convey. It does not describe cost, latency, or whether a failed/unknown address behaves differently, so it stops short of 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, front-loaded with the action and the score output, with the read-only guarantee and remediation link closing it out. The checklist is long but each item is a distinct check that carries informational weight; there is no filler or repetition.

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 carries the burden of describing results and does so: a 0-100 safety score, itemized findings, locked-SOL totals, and a fix-it link. Combined with the read-only annotation and a fully documented single parameter, an agent has everything needed to select and call it correctly.

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?

There is a single required parameter with 100% schema description coverage, and the schema already states it is the base58 public key to check. The description adds no format, validation, or edge-case detail about the address beyond what the schema provides, so the baseline of 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 uses a specific verb and resource ('Checks a Solana wallet') and then enumerates the exact risk classes examined: token approvals, phishing airdrops, Token-2022 permanent delegates, transfer restrictions, stake/nonce accounts, and account takeover. It also states the produced artifact, a 0-100 safety score, which is enough to distinguish it from the narrower sibling listers without opening their schemas.

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?

Usage is only implied: the breadth of the checklist suggests this is the comprehensive assessment tool versus the narrower list_empty_token_accounts and list_token_approvals siblings, but no sentence says when to prefer this over them or when it is unnecessary. There are no exclusions, prerequisites, or cost/latency warnings.

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