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

The description goes beyond annotations by explaining the output behavior (near-duplicate flagging) and explicitly stating 'No writes', which complements the readOnlyHint=false annotation. It does not describe error handling or rate limits, but the annotations cover the basic safety profile, so the added context earns a high score.

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 single, well-structured sentence that packs essential information (input, output, optional parameter, and next step) without redundancy. The key details are front-loaded.

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?

Despite lacking an output schema, the description explains the return format (3-6 angles with title, intent, editorial positioning) and the flagging behavior. It also provides the next step (add_radar_topic) and covers the main parameters, making the tool's behavior fully understandable for an agent.

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 references most parameters ('signalObservationId', 'topicIndex', 'customPov') and clarifies their roles (e.g., 'by signalObservationId + topicIndex' and 'Optionally pass customPov'). While projectId is not explicitly described, the description adds meaning beyond the raw schema and covers the core parameters.

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 clearly states the tool's verb ('Expand'), the resource ('radar topic'), and the specific output ('3-6 candidate article angles with title, intent, and editorial positioning'). It also indicates a distinct behavior (flagging near-duplicates) and distinguishes the tool from siblings like add_radar_topic by noting the follow-up step.

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 provides clear usage context: it explains the input parameters ('by signalObservationId + topicIndex'), the optional customPov, and explicitly notes that this tool does not write, guiding the agent to pass results to add_radar_topic. This effectively tells when to use this tool versus alternatives.

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