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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the bar is lower, and the description still adds real context: the assessment is 'heuristic', contract checks are conditional on chain support, and the return payload is a 0–100 score where higher means riskier plus a level and per-signal explanations. The only gap is that 'supported chain' is not enumerated and no accuracy/limitation caveat is given for the heuristic.

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 sentences, front-loaded with the purpose before the checklist and the return shape. The parenthetical signal list is dense but earns its place because those checks are the tool's differentiator; nothing is redundant with the title.

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?

There is no output schema, so the description carries the burden of describing the return value, and it does: score range, direction of the scale, level, and per-signal explanations. Combined with the conditional-scope caveat and the get_token identifier reference, an agent has everything needed to call this correctly and interpret the result.

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% — both `token` (CoinGecko id, symbol, name, or contract address) and `chain` (enum of eight chains, 'Chain hint when passing a contract address') are already fully documented. The description only restates the identifier convention via a pointer to get_token and never explains what happens if `chain` is omitted when a contract address is supplied, which is the one non-obvious parameter interaction. Baseline 3 is appropriate.

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 verb and resource ('Heuristic risk assessment for a token') and then enumerates the exact checks performed (honeypot, mintable, ownership, taxes, holder concentration, LP lock) plus market signals and provenance. The closing line 'Accepts the same identifiers as get_token' explicitly anchors it against a sibling, so an agent can tell it apart from get_token/get_market_data without opening any schema.

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?

Gives a concrete applicability condition — contract-level checks only apply 'where a contract address is known on a supported chain' — which pre-empts calling it with a bare symbol and expecting honeypot results. It does not explicitly contrast with get_market_data or say when the risk tool should be preferred over plain market data, so it stops short of full when/when-not routing.

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