Latest Events

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

Beyond the readOnly/idempotent annotations, the description discloses the pruning limit, the exact return shape for offset+limit beyond the newest slice ([]), and that events are returned newest-first. No contradictions with annotations.

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 a tight paragraph: resource, row schema, filter semantics, pruning behavior, alternative subscription channel, and an example—all in five dense but efficient sentences. No filler.

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 read-only list tool with an output schema present, the description covers the core data, filtering, pagination edge cases, and alternative delivery mechanism. An agent has everything needed to invoke it correctly.

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 0% schema coverage, the description fully compensates: it defines 'kind' by listing the valid detector names, explains 'offset' as pagination past the newest slice, and 'limit' through the pagination semantics and a concrete example.

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 with 'Latest anomaly events from our detectors' and names the four concrete event kinds, which makes the resource and scope unmistakable. It also defines the row structure (ts, kind, subject, payload), distinguishing it from the trading/market sibling tools.

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 explains the optional kind filter, how limit and offset interact, and the pruning behavior at 5000 events. It also points to webhooks/Telegram for alert-style consumption, giving an explicit alternative to polling this endpoint.

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