Skip to main content
Glama

VeritaHire live jobs

Record an application on the person's VH Applications page

save_application
Idempotent

For a connected person: records an application you made with them, with the resume and cover letter text that was sent, so they can open it when the employer calls. If the person says they applied, record it as applied; add confirmation when you saw the employer's own confirmation words. status ready = documents ready, not applied yet.

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": {
      "employer": "<employer>",
      "title": "<title>"
    },
    "name": "save_application"
  }
}

Input Schema

NameRequiredDescriptionDefault
payNo
titleYes
job_idNoVeritaHire job id, if the job came from search_live_jobs
statusNoapplied
employerYes
locationNo
applied_onNoYYYY-MM-DD (default today)
cover_textNoThe cover letter as sent, plain text
portal_urlNo
resume_textNoThe resume as sent, plain text
access_tokenNoNot needed when the person signed in through your Connect / sign-in button (OAuth). Otherwise the access_token from finish_connecting.
confirmationNoOptional: the employer's confirmation words, verbatim, when seen

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / access_token / description
      Previous value: -"From finish_connecting"New value: +"Not needed when the person signed in through your Connect / sign-in button (OAuth). Otherwise the access_token from finish_connecting."
    • changedInput schema / required
      Previous value: -[
      -  "access_token",
      -  "employer",
      -  "title"
      -]New value: +[
      +  "employer",
      +  "title"
      +]
  2. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false. The description adds real value beyond that by disclosing the visibility consequence ('so they can open it when the employer calls') and the connection prerequisite ('For a connected person'), but it says nothing about what happens on a repeat save for the same employer/title, even though idempotency is asserted in annotations.

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?

Three sentences, front-loaded with the purpose and the shared-visibility rationale, followed by the status decision rules. The middle clause ('with the resume and cover letter text that was sent, so they can open it when the employer calls') is slightly dense but every sentence carries distinct information.

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

Completeness3/5

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

For a write tool with 12 parameters and no output schema, the description covers the core judgement call (applied vs ready) but omits what happens on duplicate saves, what a non-connected person case looks like, and any indication of the failure mode when access_token is missing. Adequate but with clear gaps given the tool's complexity.

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

Parameters3/5

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

With 12 parameters at 50% schema coverage, the description usefully clarifies the two fuzzy ones: the applied-vs-ready meaning of status and the verbatim nature of confirmation. However, several parameters with no schema description (pay, location, portal_url) receive no meaning from the description, and employer/title/format conventions like the applied_on date are left to the schema.

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

Purpose4/5

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

States a specific verb and resource ('records an application') paired with the audience ('on the person's VH Applications page') and the payload ('resume and cover letter text that was sent' that we 'made with them'). It is clearly distinct from the read-side sibling get_my_applications, though it does not explicitly name that sibling or any other alternative.

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

Usage Guidelines4/5

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

Provides concrete decision rules for the ambiguous status parameter: 'If the person says they applied, record it as applied' and 'status ready = documents ready, not applied yet', plus when to add confirmation ('when you saw the employer's own confirmation words'). It lacks any statement of when NOT to use this tool or which sibling to prefer instead.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources