Selenios

Update application form field

update_screening_form_field

DestructiveIdempotent

Change one existing field of the application form of a job position: whether it is required, whether an answer outside the expected one disqualifies the candidate (knockout), its expected answer (expectedAnswer), the unit of an amount field (currency + period, both or neither) and, on the address field "neighborhoodLocation" only, the maximum commute distance in kilometres. fieldName is the key in configuration.formSchema.properties of the position's screening configuration, and fieldLabel is that property's title, verbatim; a label that does not match is rejected. A knockout must be a required field with a complete expected answer (on the address field, maxDistanceKm). The base fields firstName, lastName and email are always required. On a professional application, linkedinUrl or resumeFile must stay required: making the only required one of the two optional is rejected. The response reports criteriaVersionChanged: when true, the position's existing scores were computed against the previous form.

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": {
      "jobDescriptionId": "<jobDescriptionId>",
      "fieldName": "<fieldName>",
      "fieldLabel": "<fieldLabel>"
    },
    "name": "update_screening_form_field"
  }
}

Input Schema

Name	Required	Description
`period`	No	Period the amounts cover. Required together with currency.
`currency`	No	ISO currency code the amounts are expressed in (e.g. USD). Required together with period.
`required`	No	Whether the candidate must answer this field
`fieldName`	Yes	Schema key of the field, from configuration.formSchema.properties
`fieldLabel`	Yes	The title of that property, verbatim. Shown to the user on the confirmation card; a label that does not match the field is rejected.
`isKnockout`	No	Whether an answer outside the expected one disqualifies the candidate automatically
`maxDistanceKm`	No	Maximum commute distance in kilometres, for the "neighborhoodLocation" field only. Setting it turns the expected answer on.
`expectedAnswer`	No	The expected answer. Setting it turns the expectation on. A knockout also needs the field to be required.
`jobDescriptionId`	Yes	The job position ID
`expectedAnswerEnabled`	No	Whether the expected answer of this field is applied at all. Pass false to stop applying it while keeping the configured value; it also clears the knockout.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 29, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already declare destructive and idempotent behavior, but the description adds substantial context: label mismatch rejection, knockout dependency on required plus complete expected answer, base fields always required, the professional-application linkedinUrl/resumeFile constraint, and the response flag criteriaVersionChanged when existing scores were computed against the previous form.

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?

The description is dense but front-loaded around the core action and then layers validation rules efficiently. It is appropriately sized for a complex mutation tool, though bullets or sentence breaks could make the long paragraph easier to scan.

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 10-parameter destructive mutation with no output schema, the description covers most business-critical behavior and explicitly describes the criteriaVersionChanged response field. It omits some useful details such as partial-update semantics, permission requirements, and the rest of the response shape, but the core invocation guidance is strong.

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 coverage is 100%, so the schema already documents individual parameters well. The description still adds valuable cross-parameter semantics: fieldName is the schema key and fieldLabel must be its title verbatim, currency and period must be supplied together, maxDistanceKm applies only to neighborhoodLocation, and knockout requires a required field with a complete expected answer.

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?

The description opens with a specific verb and resource: "Change one existing field of the application form of a job position." The word "existing" distinguishes this from add/remove/reorder siblings, and the list of updatable attributes makes the scope concrete.

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

Usage Guidelines3/5

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

It clearly implies this tool updates an existing field and supplies many domain constraints, but it does not explicitly say when to use it instead of add_screening_form_field, remove_screening_form_field, or update_screening_questions. Prerequisites such as needing an existing screening configuration are only implied.

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

All Selenios 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?