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

Beyond the readOnlyHint=true and destructiveHint=false annotations, the description adds meaningful behavioral context: the output shape (medians and bands), the data provenance ('Source: BLS and Stratalize SIA-style composite'), and the cost ('$0.02 USDC per call'). The worked example also signals output format and how to interpret it (percent above market, renegotiation recovery). No contradiction with annotations exists.

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 well front-loaded: use-case, return value, then example. The example sentence is long and includes illustrative recovery economics that go beyond what the tool does — slightly more than strictly necessary — but the cost disclosure and source attribution earn their place. Overall compact relative to the information conveyed.

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 carries the burden of explaining return values, and it does so via both the explicit 'medians and bands' statement and a concrete worked example with interpretation guidance. For a simple two-parameter read-only tool, this is nearly complete; only response format details (e.g., JSON shape) and the supported specialty/state list are absent.

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%, so the description must compensate, and it partially does: 'by specialty and state' plus the concrete example ('ICU travel nurse ... in Illinois') clarifies that specialty means a nursing specialty and state is a US state. However, it does not specify accepted formats (e.g., 'IL' vs 'Illinois', whether specialty names are free-form) or enumerate valid values, leaving some ambiguity for a bare string-typed schema.

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 opens with a specific use case and states exactly what the tool returns: 'bill-rate medians and bands by specialty and state.' The resource is precise — travel nurse contract bill rates — which inherently separates it from generic siblings like get_salary_benchmark and get_labor_market_benchmark. The verb 'Returns' plus the concrete domain scope make the purpose unambiguous.

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 explicitly tells the agent when to use it: 'Use when benchmarking travel nurse contract rates or negotiating with a staffing agency.' This is clear context for invocation. However, it does not name alternative tools or state when not to use it (e.g., versus get_staffing_agency_markup_analysis or get_vendor_market_rate), so it stops short of full when/when-not routing.

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