which_atsLook up the applicant tracking system (ATS) a specific large employer uses, from ResumeAI's State of ATS 2026 dataset (738 Fortune 500 / Global 2000 employers checked, 704 verified against live careers portals, June 2026 audit, re-verified July 2026). Accepts a company name or slug, e.g. 'Nike' or 'jpmorgan-chase'.
| Name | Required | Description | Default |
|---|---|---|---|
| company | Yes | Company name or slug, e.g. 'Nike' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and non-destructive. The description adds valuable context: dataset provenance, coverage counts (738 checked, 704 verified), audit dates, and input flexibility (name or slug). This goes beyond the annotations without contradicting them, though it doesn't address not-found behavior.
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, with the core action front-loaded and dataset details in the second sentence. Every clause earns its place; no redundancy or filler.
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 single-parameter, read-only lookup with no output schema, the description covers what, scope, dataset, and input format. The return value is implied by the tool name and description, though the exact response shape is not specified. This is adequate for the tool's simplicity.
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 already describes the 'company' parameter with 100% coverage. The description enriches it by giving concrete examples ('Nike', 'jpmorgan-chase') and clarifying that it accepts a name or slug, which helps the agent form valid inputs.
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 specific verb 'Look up' and resource 'applicant tracking system (ATS)' for a 'specific large employer'. It clearly distinguishes from siblings like ats_changes and list_companies by focusing on identifying the ATS for a named company.
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 clear context: use when you have a specific large employer in mind, and it defines the dataset scope (Fortune 500/Global 2000). However, it does not explicitly mention alternatives or when-not-to-use, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a clearly distinct action: ATS lookup, company listing, market stats, change feed, resume scoring, and resume retrieval. Even the two resume-related tools are unambiguous—one evaluates, the other fetches.
Naming mixes conventions: ats_changes and ats_stats use a noun-focused ats_ prefix, check_resume, get_agent_resume, and list_companies use verb_noun, and which_ats is a question-style name. All are readable and snake_case, but the patterns are not consistent.
Six tools is well-scoped for an ATS/resume data server. Each tool covers a distinct capability without redundancy or bloat.
The surface covers the domain well: employer ATS lookup, company filtering, market-share statistics, change tracking, resume scoring, and consent-gated resume retrieval. The deliberate lack of resume enumeration is a documented privacy boundary, not a gap.