UK Data: US CDC health counts

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.

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 new behavioral context by flagging that figures are provisional, lagged by several months, and include predicted values adjusted for delayed reporting. It also discloses a 1-credit cost, which an agent cannot learn from annotations. It does not describe pagination or exact response shape, keeping it below a 5.

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 opening question front-loads the topic, and the remaining sentences pack source, granularity, audience, caveats and cost efficiently. It is dense but every clause carries information; the rhetorical question is the only mildly expendable element.

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?

With no output schema, the description still sketches the return shape (month-by-month counts plus year-earlier change) and warns about provisional lag and absent drug breakdowns, which is what an agent needs to interpret results. Only minor gaps remain, such as the exact field names or unit of the year-on-year change.

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 description coverage is 100%, and the schema already documents the state code (including YC/NYC) and the 1-36 month range with defaults. The description only restates 'US or one state' and 'month by month', adding no new semantics about parameter behavior, so baseline 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 gives a specific verb+resource (returns CDC's provisional 12-month-ending count of drug overdose deaths) plus scope (US or one state), granularity (month by month with year-earlier change) and provenance (NCHS VSRR). This clearly separates it from the many drug_* siblings, which are about names, classes, uses and side effects rather than mortality statistics.

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?

It sets a clear context for use ('for journalists and policy staff tracking the fentanyl-era trend') and implies a limitation to route around ('no breakdown by drug here'), which tells an agent when this tool is not sufficient. It stops short of naming an alternative tool to use instead, so it is clear but not fully explicit about siblings.

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

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

Annotations already declare read-only, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely new context: the CDC NHSN source, the granularity (national or single state), the scope limit, and the explicit 1-credit cost.

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 opening question front-loads the purpose and the payload, source, audience and caveat follow in a compact sequence. Slightly dense in places but no sentence is wasted; the cost tag is a useful tail.

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?

With only two optional parameters and no output schema, the description carries sufficient weight: it enumerates the returned metrics and the data source. The one real gap is distinguishing this from the covid and rsv hospital-admission tools in the same family.

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 are already documented, which sets the baseline at 3. The description adds one useful nuance by saying "nationally or for one state", implying jurisdiction is a single value rather than a multi-select, as well as the weekly cadence.

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?

States a specific resource (weekly new hospital admissions for laboratory-confirmed influenza) and enumerates the metrics returned, so the agent knows exactly what it gets. It never mentions the near-identical siblings covid_hospital_admissions_weekly and rsv_hospital_admissions_weekly, so disambiguation relies on the name alone.

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 line "For planners, parents and reporters tracking the season" implies who and when, and "Hospital data only: it does not count flu cases in the community or deaths" sets a clear scope exclusion. However, it never names the covid/rsv equivalents or the wrong-condition to avoid, which is the most likely selection error here.

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

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the description is free to add other context — and it does: the upstream source, the coverage limitation (no community infections), and the 1-credit cost. It does not mention reporting lag for weekly NHSN data, which would be the one remaining behavioral caveat worth knowing.

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 a plain-language question that immediately frames the purpose, followed by the precise technical statement of what is returned. The audience sentence is slightly promotional but does carry seasonal-usage signal, so little is truly 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?

With no output schema, the description carries the return-value burden well, enumerating each measure and the national/state split. A note on data lag or the default time window would close the remaining gap for a weekly surveillance series.

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 are already documented. The description only echoes the jurisdiction dimension ('nationally or for one state') and says nothing about the weeks parameter, its 1-52 range, or the default of 4 — baseline 3 is appropriate.

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 names a specific resource and metric: weekly new hospital admissions for laboratory-confirmed RSV, with the exact breakdown (children/adults, in-hospital, ICU, season-to-date) and the source (CDC NHSN). The RSV scope cleanly separates it from the sibling flu_hospital_admissions_weekly and covid_hospital_admissions_weekly tools 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?

It gives concrete usage context ('parents of infants, paediatric services and reporters each autumn and winter') and an explicit scope exclusion ('Hospital data only; it does not count community infections'). What it lacks is explicit routing to the flu/COVID equivalents or guidance on when a different surveillance tool would be preferable.

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