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

With no annotations, the description carries full behavioral disclosure. It explains that rows are appended only on state change (deduped), the monitor runs 2x/day, and it details the alert_type enum and row fields. This gives the agent a clear model of what the tool returns and avoids false outage reports.

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 dense, multi-clause paragraph that covers many aspects but lacks clear sectioning. It is front-loaded with a surprising 'EMPTY UNTIL FIRST USE' notice before stating the core purpose, and the structure could be improved with bullet points or short sentences. Still, every sentence contains useful information.

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?

Given the absence of an output schema and annotations, the description compensates by listing the alert types, row fields, filter parameters, and the empty-state behavior. It is comprehensive enough for an agent to invoke the tool and interpret results 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?

Schema coverage is 0%, so the description must explain parameters. It clarifies ticker and since_hours as filters and provides the default for since_hours, but it does not mention limit. The schema itself provides default/min/max for limit, so the gap is minor.

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 identifies the tool as alert output from the tracked-decision monitor, listing specific alert types (status_change, earnings_imminent, interval_breach, stale_decision) and describing the data rows. This clearly distinguishes it from other alert tools like tengu_v3_alerts_active or tengu_v3_stream_alerts by scoping it to thesis transitions.

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 tells the agent to poll after decision_track (when the underlying decisions are updated) and instructs how to handle an empty result ('EMPTY UNTIL FIRST USE — not broken... Say that to the user rather than reporting an outage'). It does not name alternative tools but gives enough contextual cues for when to use it.

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