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

With annotations already declaring readOnly, openWorld, idempotent, and non-destructive behavior, the description still adds critical behavioral context: below the observed USD floor, movement is invisible to the tool. This warns about false negatives and the meaning of empty results, which is exactly the kind of detail the structured fields cannot express.

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 two short sentences with no filler, and the core subject 'Events on watched addresses' is front-loaded. The second sentence earns its place by explaining a non-obvious data limitation and referencing the correct companion tool.

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?

For a simple one-optional-parameter read-only tool, the description covers the key non-obvious gap: the USD floor and the need to check coverage. It is slightly incomplete because there is no output schema and the description does not clarify what an 'event' contains or how addresses become 'watched', but the core calling risk is well addressed.

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% for the single 'limit' parameterwing, and the description does not mention it at all. Although the parameter name and default are partially self-explanatory, the rubric requires the description to compensate when coverage is low; it does not, leaving the parameter's meaning and effect entirely to inference.

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 phrase 'Events on watched addresses' identifies the resource and scope clearly, and the title 'On-chain · Address events' reinforces it. It distinguishes itself from siblings like get_address_coverage by focusing on event data rather than coverage, though it remains an elliptical noun phrase rather than an explicit imperative sentence.

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 explicitly names get_address_coverage and instructs the agent to check it before interpreting an empty result as silence, which is a concrete when-to-call rule. It does not, however, provide broader selection criteria versus other on-chain or event-related siblings beyond this caveat.

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