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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds the materially important behavior: a $0.01 USDC charge per call drawn from a configured wallet, enforcement by budget caps, and that results are third-party data rather than instructions. The payment and prompt-injection disclosures are exactly the context an agent needs before invoking a paid, open-world tool.

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?

Four short sentences, front-loaded with purpose and price, then payment mechanics, then the safety caveat and the free alternative. Every sentence carries operational information; the product identifier '(product token.safety)' is the only mild redundancy.

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?

No output schema exists, so the description must convey what comes back, and 'safety signals' is left undefined — the agent cannot tell what fields or verdicts to expect. Payment, budget, and data-trust concerns are fully covered, but the return shape and supported chains are not.

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 100%, so chain, address, and confirm_over_cap are already documented, and the description adds nothing about them. The one behavior worth surfacing beyond the schema — that confirm_over_cap never raises session or daily caps — is present only in the schema, not the description, so this stays at the baseline.

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?

Opens with a specific statement of what is returned: safety signals for a crypto token contract, tied to the product name token.safety. It is clear enough to distinguish from unrelated siblings like market_quote or sanctions_screen, though it never says what the signals actually cover (honeypot, tax, liquidity).

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?

Explicitly routes the agent to free_sample first ('Before paying: free_sample shows a real answer of this product for free'), which is a concrete alternative with a condition. It does not state when this tool should not be used beyond the free-sample-first advice.

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