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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds context beyond these: it explains the polling cron behavior, the threshold unit (bps), and the interpretation of the list as a snapshot of what is being watched. This enriches the agent's understanding without repeating annotation data, though it does not describe response format.

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 three sentences long, with the core function in the first sentence. The second sentence explains the polling and alert mechanism, which is useful context for understanding what the watchlist represents, and the third sentence gives usage guidance. While the middle sentence could be seen as tangential, it earns its place by clarifying the tool's purpose within the alert system. The structure is front-loaded and efficient.

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 list tool with one parameter and no output schema, the description provides all necessary context: what is listed, the threshold unit, the polling context, and how to use it in conjunction with sibling tools. There is no missing information needed to call the tool 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?

The schema documents the only parameter (enabled_only) with a clear description, so schema coverage is 100%. The tool description does not add new meaning to the parameter; it only mentions the threshold unit in relation to the data, not to the parameter. Per the calibration baseline, a score of 3 is appropriate when the schema fully covers parameter semantics.

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 a specific verb-resource pair ('List the topics arb-alerts currently watches') and clearly states what is returned (topics plus thresholds). It also explicitly differentiates itself from sibling tools by naming arb_recent_alerts and arb_topic_history as the tools to use afterward, making its role unambiguous.

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 tells the agent when to use this tool: 'Use to understand WHAT is being watched before asking arb_recent_alerts or arb_topic_history.' This is a direct usage guideline that also names alternatives, leaving no ambiguity about invocation order.

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