StackFast FractWin Expert Brain

Talent Scout Review Queue

talent_scout_review_queue

Read-only

Read the account owner's own first-party Talent Scout job-search work queue for real synced board roles, draft opportunities, packets, follow-up items, and the daily reconciliation report. This is not an employer review queue, applicant screening queue, candidate ranking system, or hiring decision tool. Mailbox reconciliation runs server-side via the StackFast service-account reader. Clients MUST NOT invoke their own Gmail/email connector; if mailbox_reconciliation_status is not ok, surface the red receipt and stop instead of substituting a client-side mailbox read. Surfaces open roles, direct-URL verification needs, waiting/follow-up buckets, preference filters, and today's slate. Robert's connector resolves to tenant robert and demo rows are quarantined away. Review only; no sends or applications.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No
`run_id`	No
`status`	No
`compact`	No	Return compact queue metadata and a daily_pipeline_summary instead of heavy control-tower sections.
`profile`	No	Alias for owner_profile when reviewing stale queue items.
`tenant_id`	No
`include_items`	No	When false, return health/counts/timing only without loading queue item payloads. Use for fast connector smoke tests.
`owner_profile`	No	Optional owner preference context used to refresh stale zero-score queue items inside this tenant only.
`include_detail`	No	When true, include full queue item payloads. Defaults false so hosted MCP review_queue stays small and fast.
`include_applied`	No	Include already-applied rows. Defaults false unless explicitly reviewing follow-up history.
`include_archived`	No	Include archived, rejected, passed, stale, or already-applied rows. Defaults false for active work queues.
`include_sync_delta`	No	When true, include a guarded scout.import_delta-compatible cloud-to-BYOC queue sync payload. Defaults false.

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.

Changed3 schema fields changedJul 9, 2026

removedInput schema / properties / candidate_profile

Removed value: -{
-  "description": "Optional profile used to refresh stale zero-score queue items inside this tenant only.",
-  "type": "object"
-}

addedInput schema / properties / owner_profile

Added value: +{
+  "description": "Optional owner preference context used to refresh stale zero-score queue items inside this tenant only.",
+  "type": "object"
+}

changedInput schema / properties / profile / description

Previous value: -"Alias for candidate_profile when reviewing stale queue items."New value: +"Alias for owner_profile when reviewing stale queue items."

Changed2 schema fields changedJul 8, 2026

changedInput schema / properties / candidate_profile / description

Previous value: -"Optional profile used to rescore stale zero-score queue items inside this tenant only."New value: +"Optional profile used to refresh stale zero-score queue items inside this tenant only."

changedInput schema / properties / profile / description

Previous value: -"Alias for candidate_profile when reviewing/rescoring stale queue items."New value: +"Alias for candidate_profile when reviewing stale queue items."

Changed1 schema field changedJun 26, 2026

addedInput schema / properties / include_sync_delta

Added value: +{
+  "default": false,
+  "description": "When true, include a guarded scout.import_delta-compatible cloud-to-BYOC queue sync payload. Defaults false.",
+  "type": "boolean"
+}

Changed3 schema fields changedJun 17, 2026

addedInput schema / properties / compact

Added value: +{
+  "default": true,
+  "description": "Return compact queue metadata and a daily_pipeline_summary instead of heavy control-tower sections.",
+  "type": "boolean"
+}

addedInput schema / properties / include_detail

Added value: +{
+  "default": false,
+  "description": "When true, include full queue item payloads. Defaults false so hosted MCP review_queue stays small and fast.",
+  "type": "boolean"
+}

addedInput schema / properties / include_items

Added value: +{
+  "default": true,
+  "description": "When false, return health/counts/timing only without loading queue item payloads. Use for fast connector smoke tests.",
+  "type": "boolean"
+}

Changed2 schema fields changedJun 14, 2026

addedInput schema / properties / include_applied

Added value: +{
+  "default": false,
+  "description": "Include already-applied rows. Defaults false unless explicitly reviewing follow-up history.",
+  "type": "boolean"
+}

addedInput schema / properties / include_archived

Added value: +{
+  "default": false,
+  "description": "Include archived, rejected, passed, stale, or already-applied rows. Defaults false for active work queues.",
+  "type": "boolean"
+}

AddedJun 9, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavioral context beyond that: server-side mailbox reconciliation via StackFast service-account reader, prohibition on client-side mailbox reads, failure-handling instruction based on mailbox_reconciliation_status, tenant resolution ('Robert's connector resolves to tenant robert'), and quarantine of demo rows. No contradiction with annotations.

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

Conciseness5/5

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

The description is front-loaded with the core purpose, and every sentence earns its place: scope, exclusions, server-side behavior, required failure handling, surfaced content, tenant resolution, and the review-only restriction. It is dense but not padded, and the structure moves from what it is to what it is not to how to behave.

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 complex 12-parameter tool with an output schema, the description covers the critical decision factors: purpose, non-goals, failure handling, tenant scoping, and mutation safety. It does not explain several parameters (limit, run_id, status, tenant_id) in prose, but the schema and output schema compensate for most of that. The remaining gaps are minor given the richness of the surrounding structured metadata.

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 67%, so the schema handles many parameters. The description adds some semantic hints like 'preference filters' and 'today's slate,' but does not meaningfully explain uncovered params such as limit, run_id, status, or tenant_id beyond what their names and the schema already imply. This is adequate but not exceptional.

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: 'Read the account owner's own first-party Talent Scout job-search work queue' and enumerates the exact contents (board roles, drafts, packets, follow-ups, reconciliation report). It also explicitly distinguishes itself from employer review, applicant screening, candidate ranking, and hiring decision tools, making sibling differentiation clear.

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?

The description gives explicit when-to-use context and strong when-not-to-use guidance: it is not an employer review queue, clients must NOT substitute their own Gmail/email connector, and if mailbox_reconciliation_status is not ok the agent should surface the red receipt and stop. It also states 'Review only; no sends or applications,' clearly delimiting appropriate action.

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?