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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds useful context about data composition (unemployment, job-growth, wage indicators), refresh cadence, and output fields. However, it fails to disclose how the county is selected given the schema only has an optional 'days' parameter, and it does not mention the Gold-tier limitation for history series (only in the schema).

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 efficient, front-loading the main purpose and output fields in the first sentence, followed by clear usage and update notes. It is slightly run-on and has minor redundancy with 'refreshed on source cadence' and 'Updates: on source cadence,' but overall each sentence provides value.

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 description lists all output fields and use cases, and the schema documents the 'days' parameter. However, the lack of any explanation for how the county is selected makes the tool incomplete for its primary use. There is also no output schema, but the description does name the fields. The missing county-selection mechanism is a major contextual gap.

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 single parameter 'days' has a thorough schema description (100% coverage), which would normally yield a baseline of 3. However, the tool's core function of returning a score for a specific county has no corresponding parameter, and the description does not explain how the county is inferred or specified. This is a critical omission that the description fails to compensate for, making the tool semantically incomplete.

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 it returns a 0-100 employment health score for US counties, with a specific count (3,222) and composite indicators. The verb 'Returns' and resource are specific. However, the ability to return 'for any of 3,222 counties' is undermined by the lack of a county-selection parameter in the schema, creating some ambiguity.

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 provides explicit when-to-use guidance: 'Call when the user asks how healthy a local job market is or compares counties for hiring, siting, or lending, or when timing expansion, headcount, or county-level credit decisions.' This is clear context but lacks any exclusions or mentions of alternative tools, which would be needed for a 5.

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