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

Annotations only declare readOnlyHint and openWorldHint, so the description earns credit for disclosing the data provenance (on-chain plus issuer ledger), the semantic caveat that treasury housekeeping is issuer-internal and 'never counted as money', and the presence of a forward record alongside the Pulse score. It stops short of saying whether data is delayed, cached, or paginated.

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?

Front-loaded with the flow question, which is good, but the rest is one long comma-spliced inventory of ten return categories with no grouping or hierarchy. Because there is no output schema the enumeration earns its place, but it reads as an unstructured dump rather than a scannable summary.

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?

With no output schema, the description is the only place return values are described, and it covers sources, time window, metric names, and a key counting caveat. The remaining gap is operational: default token behavior and response shape are unstated, which is minor for a single-parameter read tool.

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 description coverage is 0%, so the description must carry the token parameter — it does name USDT and USDC and pairs each with its own page URL, implying the argument selects the asset. However, it never states whether the parameter is optional or what the default is when omitted, despite required=0.

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 opening clause 'Where USDT or USDC went over the last day' gives a concrete scope (token flow, 24h window) rather than restating the title. It does not distinguish itself from the close sibling get_stablecoin_net_mint, so an agent must infer the boundary, but the content enumerated (exchange net flow, pulse score, peg) makes the tool's identity readable.

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?

No statement of when to pick this over get_stablecoin_net_mint, get_money_flows, or get_global_flows, all of which sit adjacent in the sibling list. The 'over the last day' phrase implies a recurring-daily-snapshot use case, but there are no explicit exclusions or preconditions.

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