trace_funds

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

With no annotations, the description carries the burden and does reasonably well: it discloses the return categories, that a trace proceeds layer by layer, and that deep mode is slower but more complete (a latency/cost signal). It never explicitly says the operation is read-only or whether the target address is logged, and gives no sense of runtime 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?

Purpose and outputs are front-loaded in the first two sentences, and the deep-mode caveat comes before the usage examples, which is good ordering. The full Chinese mirror roughly doubles the length, which is defensible localization but not free — no sentence is otherwise wasted.

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?

The tool has no output schema, and the description compensates by enumerating the return fields (exposure, hops, aggregation, laundering paths). All four parameters are documented in the schema, the mode tradeoff is stated, and the use cases are given — nothing an agent needs in order to call this correctly is missing.

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 100%, so the baseline is 3. The description adds only one piece of meaning beyond the schema — that deep mode trades speed for completeness — while the ambiguous target-vs-address duplication and the auto-detect chain default are left to the schema's own text.

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?

States a specific verb and resource ("trace the flow of funds from an address or transaction, layer by layer") and enumerates what the trace yields (fund exposure, hop addresses, final aggregation, suspected laundering paths), which is far more concrete than the sibling names screen_address/check_blacklist. It stops short of naming how it differs from those siblings, even though the phrase "checking whether an incoming deposit passed through a mixer or sanctioned address" overlaps with what check_blacklist appears to do.

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?

Gives explicit use cases — "tracing stolen funds" and "checking whether an incoming deposit passed through a mixer or sanctioned address" — plus a mode tradeoff ("deep mode (slower but more complete)"). No when-not guidance or named alternative is offered, so the agent must infer that a pure blacklist lookup should go to check_blacklist instead.

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