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

Annotations already announce readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real behavioral context on top: geographic coverage (US national/states/50 largest metros, Canada national/provinces, UK national with regions folded into the national answer) and the return shape ('the page's Markdown copy with a citation line'). It does not mention caching, rate limits, or what happens with an ambiguous job title, which keeps it off a 5.

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?

Two sentences, front-loaded with the resource, then the payload, then the return format — a sensible order with no filler. The middle clause listing every metric is dense but each item carries scoping information. Slight cost in readability from the long compound sentence, but nothing is wasted.

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 read tool with no output schema, the description supplies what is needed to call it correctly: what data comes back, the geographic scope, and that the response is Markdown with a citation. Annotations already handle the safety profile, so nothing material is 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?

With schema coverage at 100%, the baseline is 3, and the description adds genuinely new meaning beyond the schema: the note that UK regions are a table on the national answer tells the agent that passing a region for the UK yields a national page rather than a region-specific feed. That is a behavioral nuance about the 'place' parameter the schema does not convey. The 'job' parameter gains no extra semantics from the description.

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 names a specific resource (official pay statistics for one job in one place) and enumerates exactly what is returned: median, 10th-90th percentiles, employment, publisher, reference period, take-home pay, and DOL wage levels. That is far more concrete than the title alone. It stops short of distinguishing itself from the sibling check_pay, so an agent cannot tell from this text which of the two single-job pay lookups to pick.

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 phrase 'for one job in one place' implies a single-entity lookup as opposed to a comparison, which hints at the boundary with compare_offers. However, there is no explicit when-to-use, when-not, or named alternative, and the overlap with check_pay is never addressed. Usage must be inferred rather than read.

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