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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds context about the data source (CMS HCRIS cost reports), the output structure (percentiles by bed size and state), and an illustrative example. This goes beyond the annotations by informing the user of the nature of the returned data and its provenance.

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 three sentences, front-loaded with the usage trigger, and every sentence provides value: the use case, the return metrics, and a concrete example with source attribution. No fluff or redundancy.

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 low complexity (two parameters, read-only) and absence of an output schema, the description explains the return values (supply cost percentage at p25/p50/p75) and provides an example of interpretation. It also cites the data source. Minor gaps like optional state behavior are not addressed, but overall it is sufficiently complete for an agent to invoke the tool correctly.

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 has no descriptions (0% coverage), so the description must compensate. It clarifies that bed_size refers to the number of beds via the example (200-bed hospital), and state is used for stratification. However, it does not specify the format for state (e.g., two-letter abbreviation) or how bed_size is interpreted (exact value or range), leaving some ambiguity.

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 benchmarks hospital supply chain efficiency against a CMS peer cohort, with a specific resource (hospital supply chain) and metrics (supply cost as percentage of operating expense at p25/p50/p75). It distinguishes from siblings like get_cms_facility_benchmark by focusing on supply chain benchmarks specifically.

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 explicitly says 'Use when benchmarking hospital supply chain efficiency against CMS peer cohort or building a materials management cost reduction case,' giving clear context for when to use the tool. It does not name alternative tools or exclusions, but the usage guidance is specific and practical.

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