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

Annotations already declare readOnlyHint, idempotentHint, etc. The description adds: 'Registry-authoritative with a static + symbol fallback' and 'Factual classification only—not a recommendation,' clarifying data sourcing and non-recommendation nature. Slightly lacks detail on response format, but output schema exists.

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 concise at ~6 lines, front-loaded with the classification purpose, and well-structured: categories, input, special cases, data source, workflow. Every sentence adds value without 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?

Given the tool's complexity (compliance implications), the description covers purpose, input, special behavior, workflow integration, and pairing. Output schema exists for return values, so no gap. Aids correct agent decision-making fully.

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%; description partially compensates by naming 'token_address (mint)' and 'symbol' and their usage. However, the third parameter 'caller_id' is not explained, leaving a gap. Adds value for two params but incomplete.

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 starts with a clear verb and resource: 'Classify a token' followed by the specific categories, distinguishing it from siblings like get_token_classification. It also details special cases (e.g., tokenized securities as equity), making purpose unambiguous.

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 states when to use—'RISK/COMPLIANCE step—classify before executing'—and consequences of 'equity' classification (geo-gating + confirm). Also pairs with get_disclaimers and references get_trading_workflow, providing complete usage context.

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