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

Annotations only convey read-only/idempotent/non-destructive hints, so the description carries the behavioral burden and does so thoroughly. It discloses keyless labor data, Census-key-requiring context that 'degrades gracefully,' non-fatal source failures, metro affecting only context and label, the labor-weighted composite banding methodology, and the informational caveat. This is far beyond what annotations or schema provide and is directly useful for invocation decisions.

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 dense but every sentence earns its place: purpose, methodology, source specifics, output format, limitations, and key behavior are all included without padding. Key scoping facts are front-loaded, and the caveats appear at the end in logical order. Despite its length, it remains efficient for the complexity it must convey.

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?

Without an output schema, the description fully compensates by explaining the return structure: headline relative-cost banding, per-dimension numbers and bandings, source-failure handling, and relative-to-national normalization. It also covers input requirements (state, optional metro), data-source caveats (Census key), and the informational nature. For a read-only composite-index tool, no critical information appears missing.

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 already documents both parameters at 100% coverage, including the required state and optional metro with an example. The description adds behavioral meaning beyond the schema by explaining that metro 'refines the Census local-context leg and the label' while labor and energy remain state-level, and by noting the state-level vs metro-level scoping. This goes beyond the baseline for fully covered schemas.

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, verb-first purpose: 'One-call comparative

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 conveys clear usage context: use this for a one-call comparative business-operating-cost read, with optional metro refinement, rather than pulling each source separately. It does not explicitly name sibling alternatives or state when not to use it, but the comparative-index framing strongly implies the intended niche. The 'Informational, not a guarantee' caveat also helps set expectations.

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