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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely non-obvious behavior: it is an official reported figure rather than a model estimate, it breaks out adult/paediatric and ICU counts plus week-on-week change and season-to-date totals, and it costs 1 credit. No pagination or volume caveats, but the remaining gaps are minor for a small fixed-shape read.

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?

Front-loaded with the question the agent is actually asking, then the payload, then the caveat and cost. The metric list is long but each item is a distinct return field an agent needs; only the parenthetical cost adds mild clutter.

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?

There is no output schema, yet the description enumerates the returned metrics, geographic granularity, data source, and explicit non-coverage. For a two-optional-parameter read tool that is everything an agent needs before calling.

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%, so both parameters (weeks, jurisdiction) are already documented, and the description only echoes geography ('nationally or for one state') without adding syntax or defaults. Baseline 3 applies since the schema does the heavy lifting.

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?

Opens with a concrete question and then states the specific resource: weekly new hospital admissions for laboratory-confirmed COVID-19 from CDC's NHSN dataset. The disease qualifier ('COVID-19') cleanly separates it from the flu_ and rsv_hospital_admissions_weekly siblings without needing to name them.

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?

Gives clear usage context — national or single-state scope — and useful exclusions ('does not count community cases, tests or deaths'), which tells an agent when this data is the wrong answer. It stops short of explicitly routing to the sibling admissions tools for flu/RSV or to community-case sources.

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