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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds meaningful context beyond that: the type of data returned, example values (18% median savings, 22% leakage rate), an implied threshold behavior ('leakage above 30% triggers mandatory compliance programs'), and the source (HFMA and CMS composite). This enriches the agent's understanding of what to expect without contradicting 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?

The description is front-loaded with the use case and returns list, followed by a concrete example and source. It is concise but packs useful illustrative detail. The example sentence adds interpretive value (what leakage rate means, threshold implication) without being verbose.

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?

For a simple read-only benchmark tool with one optional parameter and no output schema, the description covers purpose, usage context, return fields, example values, and source. The main gap is the undocumented category parameter, but overall the description provides sufficient context for the agent to select and invoke the tool in many scenarios.

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 has one optional 'category' parameter with zero description coverage (0%). The description does not explicitly explain the parameter's meaning, valid values, or default behavior. It only hints via the example 'Acute care,' leaving the agent to infer that category might be a facility type. With such low schema coverage, the description needed to compensate but largely does not.

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's purpose: 'Use when benchmarking GPO contract performance' and explicitly lists the returned metrics: 'typical GPO savings percentage, leakage rate, and top savings categories.' This specific verb+resource framing distinguishes it from sibling benchmark tools like get_hospital_supply_chain_benchmark or get_asc_benchmark by naming the GPO contract domain.

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 gives clear context on when to use the tool: 'when benchmarking GPO contract performance or building a supply chain cost reduction case for a hospital board.' This is specific and useful, though it does not explicitly mention when not to use it or name alternative tools, which would elevate it to a 5.

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