Identify handoff triggers

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Read-only. This only reports.' largely restates structured data. The addition of return keys ('JSON triggers and hook_api') is mildly useful, but with an output schema present it adds little beyond what is already machine-readable.

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?

Three short sentences, front-loaded with the action and its data scope, followed by routing and safety notes. No sentence is redundant padding.

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?

With zero parameters, an output schema, and rich annotations, the description covers everything needed to invoke the tool correctly. The one residual gap is that the notion of a 'trigger' and what the caller should do with the returned hook_api is only implied.

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 tool takes zero parameters, so there is nothing to disambiguate and the baseline applies. The description correctly implies no input is required beyond the implicit 30-day window.

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 states a concrete verb and object ('Flag models that look slow or low-throughput') and anchors it to a specific data source ('30-day Studio insights'), which is enough to distinguish it from the many list/get siblings. The only softness is that 'handoff triggers' is never defined as a concept beyond the slow/low-throughput proxy.

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 bounds scope ('This only reports') and names the alternatives that perform the actual escalation ('Use escalate_if_needed or ask_frontier to send a question to the cloud'). The agent knows both when to use it and what to reach for next.

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