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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable behavior beyond that: it details the fail-safe mechanism (unregistered or unscored tokens report tradeable=false) and explains the derived composite risk and last_verified_at. It also clarifies that trade_equity uses this same risk. These details are not redundant with annotations and help the agent understand side effects and limits.

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 structured with clear labels (e.g., 'FAIL-SAFE:') and bullet-like enumeration of the classification dimensions. It front-loads the main purpose and efficiently conveys the return fields. While somewhat long, each sentence adds substantive information, and there is minimal fluff.

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 an output schema exists, the description doesn't need to elaborate on return format extensively. It lists all expected classification dimensions and the derived composite risk. It also includes the fail-safe behavior and the relationship with trade_equity. Missing only edge-case error handling or rate limits, but these are less critical for a read-only classification tool. Overall, it's thorough for its complexity.

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%, so the description carries the burden of defining parameters. It clearly explains the main parameter 'mint_or_symbol' as input for the classification. However, the optional 'caller_id' parameter is not mentioned at all, even though it likely serves a standard identification purpose. The description partially compensates for the schema coverage gap but not fully.

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 clearly states the tool performs 'Standardised tokenized-stock classification' for a mint or symbol, specifying the exact resource and action. It also lists all the classification dimensions returned, making it easy to distinguish from generic asset classification (asset_classification) or token_info and verify_token. The phrase 'tokenized-stock' sets it apart from broader classification tools.

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?

The description gives context about the tool's purpose (tokenized-stock classification) and mentions a fail-safe behavior related to tradeable status, but it does not explicitly state when to use this tool versus alternatives like asset_classification or verify_token. It references trade_equity as an enforcer of the same risk, which hints at a related tool but doesn't provide clear when/when-not guidance.

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