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

Annotations already cover read-only and non-destructive, and the description adds genuinely useful behavioral context: static data, call once, no polling, no market or wallet data. The only nit is a faint tension between "static reference data" and idempotentHint=false, but that is a minor mismatch rather than a contradiction of what the tool does.

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 core definition and the call-once instruction come first, which is correct front-loading. The two closing sentences about public market data and the get_my_ prefix are somewhat repetitive, but they earn their place by preventing wallet-data misselection.

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?

An output schema exists, so return values need not be described. For a zero-parameter, read-only reference endpoint, the description covers purpose, usage cadence, and scope boundaries completely.

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?

With zero parameters the baseline is 4. The description reinforces that no arguments are needed by stating what the tool does and does not contain, though it adds no per-parameter detail because there is none to add.

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?

It names a specific resource (the legend/key for icons and badges on WhaleWatch feed rows) and explicitly bounds its contents (no market data, no wallets). That makes it trivially distinguishable from data-returning siblings like get_whalewatch_feed or get_token_overview.

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?

"Call it once if you need to explain what a marker on a feed row means, and do not poll it" gives both the trigger condition and an explicit prohibition. It also routes the agent away from it for wallet-scoped needs by naming the get_my_ prefix convention as the alternative.

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