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

Annotations already establish readOnlyHint=true and destructiveHint=false. The description adds valuable context: the $0.50 USDC per-call costhol, the data source (Stratalize SIA 2024-style composite), and illustrative output values. This goes beyond the annotations without contradicting them.

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 primary use case and return value, followed by a compact example, a premium insight, and the cost/source. Each sentence earns its place; the example is slightly lengthy but illustrative and not wasteful.

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?

The tool has no output schemahol, and the description sufficiently explains the response (median, low/high band, agency, specialty) plus example figures. It also includes cost and source, which are important for agent decision-making. Missing details like handling of optional parameters (e.g., when neither is provided) are minor for such a simple benchmark tool.

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 coverage is 0%, leaving the description as the sole source for parameter meaning. The description implies the two parameters by mentioning 'by agency and specialty type' and gives concrete examples (AMN Healthcare, ICU). It does not explicitly name the parameters or specify format/requirements, but it provides enough for an agent to infer the inputs.

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 states a specific action: 'Returns median markup percentage with low/high band by agency and specialty type.' It also defines the exact use case: evaluating staffing agency pricing or negotiating travel nurse/locum contracts. This clearly distinguishes the tool from broad or generic benchmark siblings like get_vendor_benchmark or get_travel_nurse_rate_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?

It explicitly frames when to use the tool: 'Use when evaluating staffing agency pricing or negotiating a travel nurse or locum contract.' However, it does not mention exclusions or alternative tools (e.g., get_travel_nurse_rate_benchmark for rate-specific comparisons), so it stops short of full discriminative guidance.

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