StackFast FractWin Expert Brain

Talent Scout Compose Application

talent_scout_compose_application

Read-only

Compose a draft-only first-party job-seeker application artifact for the account owner from a real Talent Scout queue item using JD evidence. Supports cover letter, form paste, application Q&A, telephone script, and authority analysis only; never sends, applies, screens people, ranks people, or makes hiring decisions. This does not screen applicants, rank candidates, or make hiring decisions.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`notes`	No
`title`	No	Optional lookup key. Use with company when queue_item_id is not known; exact normalized match is required.
`company`	No	Optional lookup key. Use with title when queue_item_id is not known; exact normalized match is required.
`actor_id`	No
`tenant_id`	No
`careers_url`	No	Official careers page URL when known. Helps distinguish a real posting from a generic board/root page.
`output_kind`	No		cover_letter
`voice_anchor`	No
`queue_item_id`	No
`application_id`	No	Optional ATS/portal application or requisition id, such as R110984. Resolves only to an existing Talent Scout queue/history record.
`requisition_id`	No	Alias for application_id when the id is a req/requisition id.
`writer_provider`	No	Optional writer lane override. Defaults to OpenAI when a wallet key is available; bounded_fallback stays available as a fail-closed safety net.
`canonical_job_id`	No	Optional canonical job id lookup. Resolves only to an existing Talent Scout queue/history record.
`compare_providers`	No	When true, run bounded OpenAI/Gemma/Gemini comparison receipts without exposing alternate raw drafts.
`owner_profile_text`	No	Optional private owner evidence from a resume/profile setup interview. Used for proof mapping; never returned raw.
`baseline_resume_text`	No	Optional private owner evidence override. Used only to map JD requirements to proof points; never returned raw.
`company_homepage_url`	No	Official company homepage URL for company-context evidence and human review.
`company_profile_text`	No	Optional official company-site/about/product evidence. Used to target the draft to the company context; never returned raw.
`job_description_text`	No	Manual recovery path only. Paste the full JD when the ATS blocks or JS-renders and Talent Scout returns needs_jd_hydration.
`linkedin_profile_text`	No	Optional manual LinkedIn profile paste/export when LinkedIn blocks automated fetch. Used as owner evidence; never returned raw.
`portal_application_id`	No	Alias for application_id when the id came from an external portal.
`user_supplied_jd_text`	No	Alias for job_description_text; treated as authoritative user-supplied JD evidence after auto-hydration fails.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	No
`public_tool`	Yes
`drafts_never_sends`	No
`no_autonomous_outbound`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedJul 9, 2026

removedInput schema / properties / applicant_profile_text

Removed value: -{
-  "description": "Optional private owner evidence from a resume/profile setup interview. Used for proof mapping; never returned raw.",
-  "type": "string"
-}

addedInput schema / properties / owner_profile_text

Added value: +{
+  "description": "Optional private owner evidence from a resume/profile setup interview. Used for proof mapping; never returned raw.",
+  "type": "string"
+}

Changed4 schema fields changedJul 8, 2026

changedInput schema / properties / applicant_profile_text / description

Previous value: -"Optional private applicant evidence from a resume/profile setup interview. Used for proof mapping; never returned raw."New value: +"Optional private owner evidence from a resume/profile setup interview. Used for proof mapping; never returned raw."

changedInput schema / properties / baseline_resume_text / description

Previous value: -"Optional private candidate evidence override. Used only to map JD requirements to proof points; never returned raw."New value: +"Optional private owner evidence override. Used only to map JD requirements to proof points; never returned raw."

changedInput schema / properties / linkedin_profile_text / description

Previous value: -"Optional manual LinkedIn profile paste/export when LinkedIn blocks automated fetch. Used as applicant evidence; never returned raw."New value: +"Optional manual LinkedIn profile paste/export when LinkedIn blocks automated fetch. Used as owner evidence; never returned raw."

changedInput schema / properties / portal_application_id / description

Previous value: -"Alias for application_id when the id came from a candidate portal."New value: +"Alias for application_id when the id came from an external portal."

Changed4 schema fields changedJul 8, 2026

addedInput schema / properties / application_id

Added value: +{
+  "description": "Optional ATS/portal application or requisition id, such as R110984. Resolves only to an existing Talent Scout queue/history record.",
+  "type": "string"
+}

addedInput schema / properties / canonical_job_id

Added value: +{
+  "description": "Optional canonical job id lookup. Resolves only to an existing Talent Scout queue/history record.",
+  "type": "string"
+}

addedInput schema / properties / portal_application_id

Added value: +{
+  "description": "Alias for application_id when the id came from a candidate portal.",
+  "type": "string"
+}

addedInput schema / properties / requisition_id

Added value: +{
+  "description": "Alias for application_id when the id is a req/requisition id.",
+  "type": "string"
+}

Changed8 schema fields changedJun 18, 2026

addedInput schema / properties / applicant_profile_text

Added value: +{
+  "description": "Optional private applicant evidence from a resume/profile setup interview. Used for proof mapping; never returned raw.",
+  "type": "string"
+}

addedInput schema / properties / baseline_resume_text

Added value: +{
+  "description": "Optional private candidate evidence override. Used only to map JD requirements to proof points; never returned raw.",
+  "type": "string"
+}

addedInput schema / properties / careers_url

Added value: +{
+  "description": "Official careers page URL when known. Helps distinguish a real posting from a generic board/root page.",
+  "type": "string"
+}

addedInput schema / properties / company_homepage_url

Added value: +{
+  "description": "Official company homepage URL for company-context evidence and human review.",
+  "type": "string"
+}

addedInput schema / properties / company_profile_text

Added value: +{
+  "description": "Optional official company-site/about/product evidence. Used to target the draft to the company context; never returned raw.",
+  "type": "string"
+}

addedInput schema / properties / job_description_text

Added value: +{
+  "description": "Manual recovery path only. Paste the full JD when the ATS blocks or JS-renders and Talent Scout returns needs_jd_hydration.",
+  "type": "string"
+}

addedInput schema / properties / linkedin_profile_text

Added value: +{
+  "description": "Optional manual LinkedIn profile paste/export when LinkedIn blocks automated fetch. Used as applicant evidence; never returned raw.",
+  "type": "string"
+}

addedInput schema / properties / user_supplied_jd_text

Added value: +{
+  "description": "Alias for job_description_text; treated as authoritative user-supplied JD evidence after auto-hydration fails.",
+  "type": "string"
+}

Changed3 schema fields changedJun 18, 2026

addedInput schema / properties / company

Added value: +{
+  "description": "Optional lookup key. Use with title when queue_item_id is not known; exact normalized match is required.",
+  "type": "string"
+}

addedInput schema / properties / title

Added value: +{
+  "description": "Optional lookup key. Use with company when queue_item_id is not known; exact normalized match is required.",
+  "type": "string"
+}

removedInput schema / required
```
Removed value: -[
-  "queue_item_id"
-]
```

Changed2 schema fields changedJun 18, 2026

addedInput schema / properties / compare_providers

Added value: +{
+  "default": false,
+  "description": "When true, run bounded OpenAI/Gemma/Gemini comparison receipts without exposing alternate raw drafts.",
+  "type": "boolean"
+}

addedInput schema / properties / writer_provider

Added value: +{
+  "description": "Optional writer lane override. Defaults to OpenAI when a wallet key is available; bounded_fallback stays available as a fail-closed safety net.",
+  "enum": [
+    "openai",
+    "google_gemini",
+    "gemma",
+    "bounded_fallback"
+  ],
+  "type": "string"
+}

AddedJun 9, 2026

TDQS

A4/5.0

Behavior4/5

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

With readOnlyHint and destructiveHint already declaring a safe, non-destructive profile, the description adds useful behavioral context: 'draft-only', the supported output kinds, and the explicit exclusions about sending, applying, screening, and ranking. This goes beyond the annotations without contradicting them.

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

Conciseness3/5

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

The key facts are front-loaded, but the final sentence ('This does not screen applicants, rank candidates, or make hiring decisions.') largely repeats the exclusions already stated in the previous sentence. The description is not bloated overall, but the redundancy means not every sentence earns its place.

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?

Given the complexity of 22 optional parameters and the presence of a rich schema plus output schema, the description provides enough top-level context: it names the operation, the source constraint, the supported outputs, and the prohibited actions. It does not need to enumerate every lookup alias because the schema already covers those details.

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?

Schema description coverage is 73%, so the input schema already carries most parameter meaning. The description itself does not explain any parameters, but the high coverage and detailed per-parameter descriptions establish a baseline 3; it neither compensates for gaps nor adds redundant parameter detail.

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: 'Compose a draft-only first-party job-seeker application artifact.' It further clarifies the source ('from a real Talent Scout queue item using JD evidence') and enumerates the supported output kinds, which distinguishes it from sibling tools like talent_scout_record_application or talent_scout_draft_outreach.

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?

The description gives clear context: this tool is for drafting job-seeker application artifacts from queue items and JD evidence, and it explicitly states what it never does ('never sends, applies, screens people, ranks people, or makes hiring decisions'). It does not name alternative tools for those excluded actions, so it falls just short of full routing guidance.

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

All StackFast FractWin Expert Brain 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?