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

Annotations already cover read-only safety (readOnlyHint=true, destructiveHint=false). The description adds useful behavioral context: data source (BLS OES 2024), cost ($0.02 per call), and an illustrative output 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?

Description is compact and front-loaded: use cases first, then output, example, source, and cost. Every sentence adds value, though the example is somewhat lengthy. It is efficient without being sparse.

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 two-parameter tool with no output schema, the description covers purpose, output, example, source, and cost. It doesn't address error handling or state optionality, but it is fairly complete given its complexity.

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 mentions 'by specialty and state' and gives a concrete example (Illinois cardiologist), but does not specify valid values, formats, or that state is optional (schema shows only specialty as required). It adds some meaning but leaves gaps.

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?

Description states a specific verb ('Returns') and resource ('median total compensation by specialty and state from BLS OES 2024 data'), and explicitly names use cases that distinguish it from generic benchmarking tools. The physician employment context and example make it easy to differentiate from siblings like get_salary_benchmark.

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?

Provides clear when-to-use context: evaluating physician employment agreements, benchmarking compensation for recruitment, or preparing a medical staff compensation report. However, it does not name alternative tools or explicitly state when not to use this tool, so it stops short of full routing guidance.

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