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

Annotations already mark readOnlyHint=true and destructiveHint=false; the description adds useful behavior context: it is a lookup that returns peer-group context, percentiles, metadata, source attribution, and optional database_row detail, and it discloses the per-call cost of $0.02. No contradictions with annotations.

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?

Four sentences, all substantive: use case, return payload, concrete example, source/pricing. The example earns its place by grounding parameter semantics; no fluff.

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 and 0% schema descriptions, the description compensates by listing return components and the matching basis. It also includes source attribution and pricing, making it actionable for an agent choosing whether to call. Minor gaps (exact value formats) remain, but overall complete.

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 has 0% description coverage, so the description must carry meaning. It explains the matching logic ('by bed size, state, and hospital type') and gives a concrete 300-bed Illinois example. However, it does not specify formats (e.g., state abbreviation vs full name, allowed hospital_type values), leaving ambiguity for the agent.

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 action: benchmarking hospital operating costs against a CMS peer cohort and returns named output components (peer_group context, benchmark_percentiles, metadata). The 'by bed size, state, and hospital type' phrasing immediately distinguishes it from sibling hospital/benchmark tools.

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?

Leads with an explicit 'Use when...' clause that names the benchmark scenario and even a presentation use case. It does not name alternatives or exclusion criteria, so it earns a 4 rather than 5.

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