What just broke on-chain

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

Annotations already mark the tool as read-only and non-destructive, and the description adds meaningful behavioral context: results are windowed, change as the chain state changes, and are meant for polling. The signal definitions also set expectations about the shape of anomalies, going beyond what the annotations provide.

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?

Four compact sentences front-load the core 'watch feed' identity and the anomaly list before moving to polling and follow-up instructions. Every sentence contributes either definition, usage, or routing information with no redundant boilerplate.

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 read-only, non-destructive feed tool with an output schema and no required parameters, the description covers what it returns, how to filter, how to widen the window, and what to do with a result. Combined with annotations and schema, nothing essential is missing for selecting and invoking the 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?

The description explains how to use signal and since_s, adding usage nuance beyond their schema descriptions. Chain and limit are not explicitly described, but their schema metadata (enum, default, min, max) makes them self-explanatory, so the 50% schema coverage is adequately compensated.

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 opens by explicitly framing the tool as a watch feed, not a per-token lookup, and states that it returns tokens that just changed on-chain state within a window. It then enumerates four concrete anomaly types, giving a specific verb+resource definition that clearly distinguishes it from siblings like token_report and honeypot_check.

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?

It explicitly instructs the agent to poll this tool on an interval instead of scanning tokens manually, which is clear when-to-use guidance. It also tells the agent to call token_report to vet a flagged token, giving a concrete follow-up path and routing away from per-token lookup tools.

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