FedSalary: official pay data

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered; the description adds real behavioral context beyond that. It discloses the derived outputs (percentile span, median, net take-home after federal and state tax, DOL wage level) and scopes them geographically (US tax, US metro wage levels, UK year-only). It does not say what happens on unsupported places or out-of-range pay figures, which holds it at a 4.

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?

It is a single dense sentence with the core computation front-loaded and the output list trailing, so an agent gets the gist immediately. Nothing is filler, but the run-on structure of the enumerated outputs makes it slightly harder to scan than a short bulleted form would be.

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?

There is no output schema, so the description must carry the return-value burden, and it does: it names each returned figure and the conditions under which the DOL wage level applies. With five parameters fully documented in the schema and annotations covering safety and idempotency, nothing an agent needs to call this correctly 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?

Schema coverage is 100%, so the baseline is 3, but the description earns more: stating that take-home is computed 'at the midpoint' tells the agent how min and max combine into a single figure, which the schema never says. Framing min as 'the low end of the range, or the only figure' also clarifies that a single number is a valid call. That is genuine meaning added on top of a fully documented 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 states a precise computation: where a given offer or posted range falls on the official pay distribution, returning percentile span, median, US take-home pay, and DOL wage level. That is far more specific than the name alone. It references get_pay only to inherit its place coverage, so the boundary with compare_offers (also a sibling) is never drawn, which keeps it from a 5.

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?

Usage is implied by the framing ('a job offer's pay, or a posted pay range'), which tells an agent this is for evaluating a concrete figure rather than browsing a distribution. There is no explicit when-to-use/when-not statement and no guidance on choosing between this, get_pay, and compare_offers. The reference to get_pay clarifies shared place coverage but not task selection.

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

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

Annotations already cover read-only, idempotent, non-destructive, closed-world behaviour, so the description is freed to add methodology: which taxes are modeled (federal, Social Security, Medicare, state), that BEA regional price parities including rent drive the cost adjustment, and an explicit exclusion of city and county income taxes. That exclusion is exactly the kind of scope caveat an agent needs; only error handling and place-resolution failure modes are unstated.

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?

Three sentences, no filler, with the comparison setup first and the return payload enumerated afterward. The opening clause 'each a pay figure in a state or one of the 50 largest metro areas' is slightly compressed/awkward but earns its place as a scope constraint.

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 describing returns, and it does so thoroughly (take-home, take-home at national prices, comparison verdict and magnitude, matching salary, optional distribution placement). For a 6-parameter analysis tool that is nearly complete; invalid-place behaviour is the only notable omission.

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 100%, so all six parameters are already documented and the baseline is 3. The description adds little beyond the schema: it ties the job parameter to the distribution output and narrows places to 'a state or one of the 50 largest metro areas', but says nothing about unit handling (year vs hour) or pay formatting that the schema does not already cover.

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 operation on a specific resource: two US job offers compared after federal/state tax and regional prices. It is clearly distinct from get_pay and check_pay (single-figure lookups) even though it never names a sibling explicitly.

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?

Usage is implied by the scenario ('two US job offers') and the optional job parameter is described as adding distribution placement, but there is no explicit when-to-use/when-not guidance or routing to get_pay/check_pay for single-figure checks.

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

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

Annotations already declare read-only, idempotent, non-destructive, but the description adds substantial behavior the agent could not otherwise know: data provenance (employers' documented APIs, refreshed weekly), the BLS-median fallback when no range is published, geographic scoping of that fallback, and default ordering. The coverage caveat ('few or no results does not mean no such jobs exist') is exactly the kind of failure-mode disclosure that prevents a bad conclusion from an empty result.

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?

Front-loaded with what it returns and from where, then caveats, then scope limits; each segment carries information. The middle sentence listing result fields is long and semicolon-chained, and the dense packaging makes it harder to scan than it needs to be for a five-parameter search tool.

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 correctly takes on the burden of describing return fields, and it explains the pay-derivation logic and coverage gaps thoroughly. The remaining gap is operational: it never states how many results are returned or whether result sets are capped/paginated, which matters for a search 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 description coverage is 100%, so all five parameters are already documented, including the default for sort and the min_pay rule that jobs without published pay drop out. The description adds little parameter-level meaning beyond the schema; it only restates keyword-and-place matching and mentions the pay-range sort superficially.

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?

States a specific verb and resource (find current job openings) plus scope: employers' own job boards in the US and Canada, matched by keywords and place. The result contract (title, employer, places, date, pay or BLS median, distribution position, apply link) makes it clearly distinguishable from the pay-lookup siblings check_pay/get_pay/compare_offers.

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?

Gives clear context for when it applies (keyword + place job search over live postings) and useful boundaries: no job descriptions, takes no applications. It stops short of naming alternatives, e.g. it never says when to use check_pay or get_pay instead when the user only wants salary data, so routing between siblings is left implicit.

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

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.