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

Annotations already declare readOnlyHint=true and destructiveHint=false, lowering the burden. The description adds genuine value on top: a $0.10 USDC per-call price, the data source ('Stratalize static model derived from published 340B savings ranges'), and an illustrative worked example. No contradiction 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, heavily front-loaded with the usage trigger, followed by outputs, an example, source, and cost. The example is somewhat verbose but earns its place by showing realistic call intent. Each sentence adds information; nothing is filler.

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 correctly carries return-value disclosure, listing all key outputs. For a read-only benchmark tool it covers usage, outputs, an example, source, and pricing. Remaining gaps are per-parameter behavior (especially state and annual_pharmacy_spend), but the core calling contract is adequately specified.

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 0%, so the description must compensate. It partially does: the 250-bed community hospital example hints at bed_size, 'adjusted patient day' maps to annual_patient_days, and the 340B savings output implies enrolled_340b's role. But state and annual_pharmacy_spend are never given explicit meaning, and parameters are not individually mapped.

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 verb+resource ('benchmarking hospital pharmacy costs') and enumerates concrete outputs: drug cost per adjusted patient day, 340B savings opportunity, specialty drug drivers, and GPO targets by bed size. This clearly distinguishes it from siblings like get_nadac_drug_benchmark (drug pricing) and get_gpo_contract_benchmark (contract data).

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 opens with an explicit 'Use when benchmarking hospital pharmacy costs or building a pharmacy cost reduction strategy for a board presentation,' giving clear invocation context. However, it never names alternatives or when-not-to-use conditions, which would matter given the huge sibling list.

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