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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description supplements this with useful behavioral context: data availability from 2020-07-15 onward, no authentication required, and 'unlimited free' usage. It also clarifies the data source (HHS Protect via CMU Delphi), which exceeds what annotations alone convey. No contradictions.

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 four sentences, each serving a purpose: what it does, what it returns, data availability, and usage notes. Information is front-loaded with the core function firstaint. No filler; efficient and well-structured.

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 required parameters, a fully described schema, and an output schema present, the description covers all necessary context: data source, metrics, temporal scope, multi-state/date-range capability, and access constraints. Nothing an agent needs to call this tool correctly is missing, and the output schema handles return value details.

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 schema covers both parameters (states and dates) with descriptions that already include YYYYMMDD format, range syntax, and availability from 2020-07-15. The description's mention of multi-state queries and date formats is redundant with the schema. Since schema coverage is 100% and the description adds no additional parameter meaning, the baseline of 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 opens with a specific verb ('Retrieve') and a precise resource: daily COVID-19 hospitalization data from HHS Protect via CMU Delphi for US states. It enumerates the exact metrics returned (adult/pediatric ICU/hospital counts, admissions, bed utilization), which clearly differentiates it from other COVID-related tools like delphi.covid.covidcast or disease.covid.country. The source and scope make the tool's purpose 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 provides clear context for when to use the tool: 'Useful for tracking pandemic hospital burden over time.' It also mentions support for multi-state queries and date ranges, which are key usage patterns. However, it does not explicitly state when not to use it or name alternative tools for other COVID metrics, so it stops short of providing exclusions.

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