Get Attention

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context: it returns a ranked list, each item includes a plain-English reason and where to fix it, and it advises proactively offering help. This goes beyond the annotations and clarifies the tool's output style and suggested follow-up action.

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 two sentences, but the first is a long enumerative sentence listing many categories. While every sentence earns its place and the main action is front-loaded ('Return the proactive, ranked list...'), the list of examples could be slightly condensed without losing meaning. It is still well-structured and informative.

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 tool has no parameters and no output schema, the description provides sufficient context: it describes what the list contains, the use cases, and the format of each item (reason and where to fix it). It does not mention pagination or limits, but for a 0-param tool this is not a significant gap. It is complete enough for an agent to invoke 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 tool has zero parameters, and the input schema is an empty object with 100% schema description coverage. Per the rubric, a baseline of 4 is appropriate when there are no parameters. The description does not need to explain parameter semantics, and it correctly focuses on the tool's behavior and output.

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 returns a proactive, ranked list of everything needing the user's attention across the account, with specific examples (missing bank statements, unreconciled transactions, deadlines, etc.). This distinguishes it from sibling tools like get_deadlines or get_tasks, which focus on narrower domains. The verb 'Return' and the resource 'ranked list of attention items' are specific and 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 enumerates trigger phrases: 'Use whenever the user asks what they need to do, what's outstanding, what's missing, whether anything needs them, for a status check or 'what should I focus on'.' This provides clear usage context. It does not explicitly mention when NOT to use it or point to alternatives, but the trigger list is comprehensive enough for an agent to select it appropriately.

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