cpu_get_attention

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

No annotations are provided, so the description carries the full burden. It discloses that items are purely descriptive and suggest no action, that data is public, that deliveries only surface for oneself, and that a `note` appears if deliveries endpoint is down. It also explains severity levels and the meaning of each flag.

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 front-loaded with the purpose and structured logically. However, it is somewhat verbose; it could be more concise while retaining all necessary detail.

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's complexity (2 optional params, no output schema), the description is fairly complete. It explains return items, severity levels, and edge cases like the deliveries endpoint being down. Minor omission: no mention of response structure, but understandable without output schema.

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 100%, earning a baseline of 3. The description adds significant value by explaining scouting behavior for `owner` and filtering logic for `minSeverity`, going beyond the schema's basic descriptions.

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 'Owner-scoped roll-up of cells worth attention, most time-sensitive first — so you skip scanning the whole map,' providing a specific verb and resource, and distinguishes it from sibling tools by its unique roll-up functionality.

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 explains when to use the tool (to skip scanning the whole map) and how to use it for self vs. other players via the `owner` parameter. It also describes filtering with `minSeverity` but does not explicitly state when not to use it or compare with alternatives.

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