Scan a job posting against 16 US state/DC pay-transparency disclosure laws.
Scored across 1 tool
With only one tool, there is no possibility of misselection or overlap. The single tool's purpose is unambiguous and clearly scoped to job-posting pay-transparency scanning.
The lone tool name follows a clear snake_case verb_noun pattern (check_job_posting_pay_transparency) and is fully descriptive. There are no other names to conflict with, so consistency is trivially satisfied.
One tool is on the thin side for a server, even though this particular tool is substantial and covers many jurisdictions internally. It is borderline: a single-purpose utility, but it offers no complementary operations (e.g., listing supported jurisdictions or retrieving statute details).
For its stated narrow purpose (flagging missing salary-range and benefits disclosures across listed jurisdictions), the tool appears functionally complete and intentionally avoids certifying compliance. Minor gaps exist, such as no way to list jurisdictional requirements or check postings in batch, but these are workaroundable.
Scan a job posting's text against US state/DC salary-range-disclosure laws (CA, CO, CT, HI, IL, MD, MA, MN, NV, NJ, NY, RI, VT, VA, WA, DC) and flag exactly which required element (salary range, benefits description) is detectably missing, with the statute citation. Conservative: never certifies a posting as compliant, only flags what's missing. Not legal advice.
| Name | Required | Description | Default |
|---|---|---|---|
| states | No | State/DC codes to check against. Defaults to all 16 covered jurisdictions if omitted. | |
| posting_text | Yes | The full text of the job posting | |
| employee_count | No | Employer's total employee count, used for laws with a minimum-employee threshold (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden, and it does unusually well: it discloses the conservative posture ('never certifies a posting as compliant, only flags what's missing') and a liability boundary ('not legal advice'). It omits practical traits such as determinism, handling of ambiguous text, or rate limits, so it falls short of 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?
Three sentences, front-loaded with the core action, each carrying distinct load: scope and output, conservative behavior guarantee, and legal disclaimer. No filler or repetition of the tool name.
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 and no annotations, the description must convey behavior and result shape, which it largely does by naming the flagged elements and citation format. It is close to complete; only edge-case behavior (e.g., postings with partial salary ranges, multiple states matching) is left unaddressed.
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 schema already documents posting_text, states (with default of all 16), and employee_count. The description adds no syntax or semantic detail beyond what the schema provides (the element names mentioned relate to output, not input), so the baseline of 3 applies.
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 (scan) and resource (job posting text) constrained to a named, enumerated set of jurisdictions, and states what it outputs (which required element is missing, with statute citation). No sibling ambiguity exists, and the tool's scope is unmistakable.
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 makes the use case clear (checking a posting against pay-transparency laws) and scopes it to US state/DC jurisdictions, plus a 'not legal advice' caveat. It does not, however, state when NOT to use it or what alternative exists for adjacent compliance questions, since there are no siblings to route to.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_job_posting_pay_transparencyCompliance lint for AI, scraping, and privacy law. Cited findings in 200 or more jurisdictions.
Contract drafting, statute-cited US state law requirements, non-compete checks, risk analysis.
Live healthcare pay data: advertised ranges by role/state/city, offer checks, transparency scores.
EU pay transparency (Directive 2023/970) and French Egapro readiness assistant. Public data only.
Add one secure layer between your agents and this server.
