Semata

Import ATS candidates

import_ats_candidates

Import 1 to 5 candidates from a connected ATS (workable, pinpoint, greenhouse or ashby) into a Semata screening, and queue their CVs for processing. Use list_ats_candidates for the candidate ids. Give destinationBatchId for an existing screening or destinationRoleId for a role's screening, not both. A closed screening is refused. Candidates already imported are skipped and reported, each import counts against the daily CV processing limit, and the call fails if the limit would be exceeded. Each candidate succeeds or fails on its own: read every entry in results. Requires OAuth or a scoped token with ATS access and a workspace role that can edit.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "workspaceId": "<workspaceId>",
      "provider": "<provider>",
      "candidateIds": "<candidateIds>"
    },
    "name": "import_ats_candidates"
  }
}

Input Schema

Name	Required	Description
`provider`	Yes
`workspaceId`	Yes	The workspace id returned by list_workspaces. Use 'personal' for the personal workspace.
`candidateIds`	Yes
`destinationRoleId`	No
`destinationBatchId`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 28, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Goes well beyond the annotations by disclosing idempotency behavior (already-imported candidates are skipped and reported), rate/quota semantics (each import counts against the daily CV processing limit, call fails if exceeded), partial-failure semantics (each candidate succeeds or fails on its own, read every entry in results), and auth requirements (OAuth or scoped token with ATS access plus an edit-capable workspace role). Only the shape of the returned results entries is left unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and scope, and every sentence adds unique operational information with no filler. The quota sentence is a comma-spliced run-on bundling three distinct rules, which slightly hurts scannability but not content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter mutation with no output schema, the description covers preconditions, idempotency, quota failure, per-candidate outcomes, and auth. The remaining gap is that it never describes what a results entry contains, leaving the agent to infer the return shape despite being told to read every entry.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% (only workspaceId is documented), so the description carries real weight: it supplies the 1–5 cardinality of candidateIds, the enumerated provider names, and the exclusivity rule between destinationBatchId and destinationRoleId that the schema does not encode. It does not explain what a 'batch' versus a 'role screening' is, which would complete the picture.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (import ATS candidates into a Semata screening), names the four supported providers, and adds the side effect of queueing CVs for processing. An agent can distinguish this from sibling source_candidates or add_sourced_candidates_to_screening without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent to list_ats_candidates to obtain ids, and states the mutually exclusive destination choice: destinationBatchId for an existing screening, destinationRoleId for a role's screening, 'not both'. It also gives the blocking condition (closed screening is refused), so the agent knows when the call will not be appropriate.

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

All Semata tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?