cdc_weekly_deaths

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

Annotations provide readOnlyHint=true, so the safe read-only nature is established. The description adds valuable behavioral context: data is provisional (subject to change), updated weekly, covers 2020–present, and includes percent_of_expected_deaths for excess mortality detection. This goes well beyond the minimal read-only annotation.

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 concise sentences. The first sentence front-loads the core purpose, and the second adds high-impact information about data freshness and the excess mortality metric. No words are wasted.

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?

Since there is no output schema, the description carries the burden of explaining what data is returned. It names the death categories and the percent_of_expected_deaths field, plus time coverage and update cadence. It does not specify the exact response structure (e.g., one row per week per state), but the essential return information is covered.

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 input schema already provides descriptions for all three parameters (year, limit, state) with 100% coverage, including examples and default behavior. The description does not add further parameter-specific detail, so the baseline of 3 applies.

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 retrieves weekly provisional death counts by state for specific causes (COVID-19, pneumonia, influenza, and total). It emphasizes the data is the most current CDC mortality data and includes percent_of_expected_deaths, which distinguishes it from sibling CDC tools like cdc_mortality_rates or cdc_causes_of_death.

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 strong contextual cues for when to use this tool: when the user needs the most current weekly provisional mortality data, updated weekly, covering 2020–present. It does not explicitly name alternatives or state when not to use it, but the emphasis on 'most current' and 'weekly' clearly signals its intended use case.

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