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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. Description adds behavioral details: it folds all non-expired signals into worst risk level, provides risk score and breakdown, and lists contributing signals worst-first. It also states 'Descriptive observed data only. Not financial advice.' There is no contradiction with annotations.

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?

The description is composed of three short paragraphs. The first gives the core action, the second clarifies relationship to sibling tool, and the third provides workflow context. It is efficient with no wasted words, though the second paragraph could be slightly more compact. Overall well-structured and front-loaded.

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?

Given that an output schema exists (context signal), the description does not need to detail return format. It covers purpose, differentiation, usage guidelines, and key behavioral details. The missing parameter explanations (limit, caller_id) are minor gaps. For a tool with four parameters and a robust annotation set, the description is largely complete.

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 0% (no schema descriptions), so description must compensate. It explains the 'subject' parameter as 'symbol or mint' and implies window_hours by referring to 'the window'. However, 'limit' and 'caller_id' are not explained. This partial coverage means the description adds some value but is insufficient for a zero-coverage situation.

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?

Description clearly states the tool does per-token risk roll-up over observed safety signals, and explicitly distinguishes it from the sibling tool get_risk_assessment by noting it complements but does not replace that tool. The verb 'get' plus 'risk assessment' is specific, and the scope ('per-token', 'recently observed') is precise.

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?

Description provides explicit workflow guidance: 'INTELLIGENCE / RISK step -- run before quoting or sizing an unfamiliar token; a critical safety signal is a hard skip condition.' It also tells when not to use it by contrasting with get_risk_assessment. This gives the agent clear when-to-use and action-triggering instructions.

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