StackFast FractWin Expert Brain

Talent Scout Record Manual Note Receipt

talent_scout_record_manual_note

Read-only

Record a human decision and receipt on a Talent Scout manual-note draft. This is closed-world tracking only: it never sends email, LinkedIn messages, phone calls, or applications automatically. Use sent_text only to store text the human already handled manually.

Input Schema

TableJSON Schema

Name	Required	Description
`goal`	No
`send`	No
`apply`	No
`notes`	No
`channel`	No
`summary`	No	Factual summary of the already-completed human outreach.
`decision`	Yes	Human decision to record. No option sends anything automatically.
`sent_text`	No	Exact text the human actually sent manually. Talent Scout stores this receipt but never sends it.
`tenant_id`	No
`draft_text`	No
`role_title`	No
`campaign_id`	No
`occurred_at`	No	ISO-8601 time the human completed the outreach.
`person_name`	No
`sqlite_path`	No	Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
`company_name`	No
`contact_name`	No
`person_label`	No
`next_touch_at`	No	Optional ISO-8601 next human follow-up time.
`queue_item_id`	No
`application_id`	No
`auth_token_key`	No	Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
`manual_note_id`	Yes
`idempotency_key`	No	Caller-stable key for the immutable relationship receipt.
`database_url_key`	No	Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
`company_target_id`	No
`edited_draft_text`	No
`tenant_database_type`	No	Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

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.

Changed9 schema fields changedAug 4, 2026

addedInput schema / properties / application_id
```
Added value: +{
+  "type": "string"
+}
```

changedInput schema / properties / channel / enum

Previous value: -[
-  "linkedin",
-  "email",
-  "phone",
-  "in_person"
-]New value: +[
+  "linkedin",
+  "email",
+  "sms",
+  "phone",
+  "in_person"
+]

addedInput schema / properties / contact_name
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / idempotency_key

Added value: +{
+  "description": "Caller-stable key for the immutable relationship receipt.",
+  "type": "string"
+}

addedInput schema / properties / next_touch_at

Added value: +{
+  "description": "Optional ISO-8601 next human follow-up time.",
+  "type": "string"
+}

addedInput schema / properties / occurred_at

Added value: +{
+  "description": "ISO-8601 time the human completed the outreach.",
+  "type": "string"
+}

addedInput schema / properties / queue_item_id
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / role_title
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / summary

Added value: +{
+  "description": "Factual summary of the already-completed human outreach.",
+  "type": "string"
+}

AddedJul 9, 2026

TDQS

A3.5/5.0

Behavior1/5

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

The description genuinely adds useful behavioral context: no automatic sends, sent_text is only stored, and decisions have no side effects except tracking. However, annotations declare readOnlyHint=true while the description says the tool records a decision and receipt, which implies a write operation. That contradiction is a severe transparency failure.

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?

Two sentences front-load the main purpose and immediately flag the critical negative behavior (never sends). Every sentence carries weight and there is no filler or redundancy.

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?

The required fields and core workflow are clear, and the output schema covers return behavior, so this is usable. However, for a 28-parameter tool the description leaves the relationships among multiple optional identifiers (queue_item_id, application_id, campaign_id, company_target_id) and routing/credential options to inference. It is adequate but has clear completeness gaps.

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 only 36% schema description coverage, the description must compensate, and it does explain the most safety-critical parameter meaning (sent_text is a receipt, not something to send). It also frames send/apply booleans as non-sending via the closed-world statement. Many optional identifiers remain unexplained in the description, though their names and the remaining schema descriptions make them largely self-evident.

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 states a specific action ('record'), a specific resource ('a Talent Scout manual-note draft'), and the precise kind of record ('a human decision and receipt'). The closed-world tracking qualification clearly separates it from outreach-sending and composition siblings.

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?

It tells the agent this tool is for already-completed human outreach and explicitly says it never sends anything, which prevents confusing it with drafting/sending tools. The instruction to use sent_text only as a stored receipt adds clear field-level guidance. It does not name alternative sibling tools explicitly, so it misses the top anchor point for that.

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?