Outreach Desk

Inbound Message Intake

intake_message

Use this only as the entry point for the interactive intake form, or when the user attaches a pitch file such as .eml or .msg. For a pitch pasted in chat, use score_message instead. With no message it returns status ready and the empty form. With a message it returns status ok, the evaluation and three reply drafts. It saves the evaluation only when the user already has a desk; otherwise it scores against a sample engineer profile, which is not the user's real score, so say so and offer set_criteria. The desk is the signed-in user's, so send no desk_key.

Input Schema

Name	Required	Description
`file`	No	Set by ChatGPT when the user opens an attached pitch file (.eml, .msg, .pitch, .outreach). Do not fill it yourself.
`sender`	No	Optional sender email address, profile URL or domain, such as "jane@stripe.com".
`channel`	No	Optional channel the pitch came from. Defaults to email.
`message`	No	Optional pitch text, such as "Hi, we are hiring a Staff Engineer at Stripe, $220k base, remote." Omit it to open the empty intake form.
`priority`	No	Optional priority the user gives this pitch. Defaults to medium.

Output Schema

Name	Required	Description
`file`	No	The attached file, when the form was opened from one.
`as_of`	No	Day of the call, as YYYY-MM-DD in UTC.
`drafts`	No	Only with status ok: one draft body for each kind of reply. Nothing is sent.
`source`	No	Where the data comes from: the user's own private desk.
`status`	Yes	ready: the empty form is open and no pitch was given. ok: the pitch was scored.
`channel`	No	Channel the pitch came from.
`message`	No	With status ready: what the user should do next. With status ok: which criteria the pitch was scored against.
`priority`	No	Priority the user gave the pitch.
`evaluation`	No	Only with status ok: the score of the pitch.
`interactive_ui`	Yes	The intake form resource.
`scored_against`	No	your_criteria: the user's saved desk criteria. sample_profile: a sample engineer profile, because the user has no desk; this is not the user's real score.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 19, 2026
- addedInput schema / properties / message / maxLength
```
Added value: +20000
```
- addedInput schema / properties / sender / maxLength
```
Added value: +320
```

Changed1 schema field changedOct 15, 2026

addedInput schema / examples

Added value: +[
+  {
+    "message": "Hi, we are hiring a Staff Engineer at Stripe, $220k base, remote.",
+    "sender": "jane@stripe.com"
+  }
+]

Changed2 schema fields changedOct 13, 2026

changedOutput schema / properties / message / description

Previous value: -"Only with status ready: what the user should do next."New value: +"With status ready: what the user should do next. With status ok: which criteria the pitch was scored against."

addedOutput schema / properties / scored_against

Added value: +{
+  "description": "your_criteria: the user's saved desk criteria. sample_profile: a sample engineer profile, because the user has no desk; this is not the user's real score.",
+  "enum": [
+    "your_criteria",
+    "sample_profile"
+  ],
+  "type": "string"
+}

Changed44 schema fields changedOct 10, 2026
- changedInput schema / properties / channel / description
```
Previous value: -"Communication channel the message was received on."New value: +"Optional channel the pitch came from. Defaults to email."
```
- changedInput schema / properties / file / description
```
Previous value: -"File metadata injected when opened through a file extension entrypoint."New value: +"Set by ChatGPT when the user opens an attached pitch file (.eml, .msg, .pitch, .outreach). Do not fill it yourself."
```
- addedInput schema / properties / file / properties / name / description
```
Added value: +"File name, such as \"lead.eml\"."
```
- addedInput schema / properties / file / properties / resourceUri / description
```
Added value: +"The host link to the file."
```
- changedInput schema / properties / message / description
```
Previous value: -"The inbound outreach or recruiter pitch text to evaluate."New value: +"Optional pitch text, such as \"Hi, we are hiring a Staff Engineer at Stripe, $220k base, remote.\" Omit it to open the empty intake form."
```
- changedInput schema / properties / priority / description
```
Previous value: -"Optional candidate priority assigned to this inbound opportunity."New value: +"Optional priority the user gives this pitch. Defaults to medium."
```
- changedInput schema / properties / sender / description
```
Previous value: -"Optional recruiter sender info (email address, URL or domain)."New value: +"Optional sender email address, profile URL or domain, such as \"jane@stripe.com\"."
```
- addedOutput schema / properties / as_of / description
```
Added value: +"Day of the call, as YYYY-MM-DD in UTC."
```
- addedOutput schema / properties / channel / description
```
Added value: +"Channel the pitch came from."
```
- addedOutput schema / properties / drafts / description
```
Added value: +"Only with status ok: one draft body for each kind of reply. Nothing is sent."
```
- addedOutput schema / properties / drafts / properties / decline / description
```
Added value: +"Draft body for a polite decline, with the feedback card appended."
```
- addedOutput schema / properties / drafts / properties / interested / description
```
Added value: +"Draft body for an interested reply."
```
- addedOutput schema / properties / drafts / properties / request_info / description
```
Added value: +"Draft body that asks for the salary range and remote policy."
```
- addedOutput schema / properties / evaluation / description
```
Added value: +"Only with status ok: the score of the pitch."
```
- addedOutput schema / properties / evaluation / properties / breakdown / description
```
Added value: +"The four sub-scores, each an integer from 0 to 100 where higher is better."
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / cadence / description
```
Added value: +"How well spaced the outreach is; low for rapid follow-ups or contact after a decline."
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / cadence / maximum
```
Added value: +100
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / cadence / minimum
```
Added value: +0
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / relevance / description
```
Added value: +"Fit with the target role, skills, salary floor and remote policy."
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / relevance / maximum
```
Added value: +100
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / relevance / minimum
```
Added value: +0
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / spam / description
```
Added value: +"Spam safety: 100 is clean, low means template tokens, buzzwords or urgency."
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / spam / maximum
```
Added value: +100
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / spam / minimum
```
Added value: +0
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / specificity / description
```
Added value: +"How concrete the pitch is: named company, role details and stated salary."
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / specificity / maximum
```
Added value: +100
```
- addedOutput schema / properties / evaluation / properties / breakdown / properties / specificity / minimum
```
Added value: +0
```
- addedOutput schema / properties / evaluation / properties / composite_score / description
```
Added value: +"Overall score from 0 to 100."
```
- addedOutput schema / properties / evaluation / properties / composite_score / maximum
```
Added value: +100
```
- addedOutput schema / properties / evaluation / properties / composite_score / minimum
```
Added value: +0
```
- addedOutput schema / properties / evaluation / properties / evaluation_id / description
```
Added value: +"Id to pass to draft_response; valid only when the user has a desk."
```
- addedOutput schema / properties / evaluation / properties / flags / description
```
Added value: +"Warning flags. Values: missing_salary, dealbreaker_clash, token_failure (unfilled template token such as [Current Company]), aggressive_drip, repeat_after_decline, slop, artificial_urgency, free_webmail. Empty when the pitch is clean."
```
- addedOutput schema / properties / evaluation / properties / key_reasons / description
```
Added value: +"Plain reasons behind the scores."
```
- addedOutput schema / properties / evaluation / properties / recommended_action / description
```
Added value: +"Suggested reply."
```
- addedOutput schema / properties / evaluation / properties / sender_domain / description
```
Added value: +"Sender domain of the pitch."
```
- addedOutput schema / properties / evaluation / properties / summary / description
```
Added value: +"Cleaned summary of the pitch."
```
- addedOutput schema / properties / file / description
```
Added value: +"The attached file, when the form was opened from one."
```
- addedOutput schema / properties / file / properties
```
Added value: +{
+  "name": {
+    "description": "File name, such as \"lead.eml\".",
+    "type": "string"
+  },
+  "resourceUri": {
+    "description": "The host link to the file, as ChatGPT sent it.",
+    "type": "string"
+  }
+}
```
- addedOutput schema / properties / file / required
```
Added value: +[
+  "name",
+  "resourceUri"
+]
```
- addedOutput schema / properties / interactive_ui / description
```
Added value: +"The intake form resource."
```
- addedOutput schema / properties / message / description
```
Added value: +"Only with status ready: what the user should do next."
```
- addedOutput schema / properties / priority / description
```
Added value: +"Priority the user gave the pitch."
```
- addedOutput schema / properties / source / description
```
Added value: +"Where the data comes from: the user's own private desk."
```
- addedOutput schema / properties / status / description
```
Added value: +"ready: the empty form is open and no pitch was given. ok: the pitch was scored."
```

Changed1 schema field changedOct 10, 2026

removedInput schema / properties / desk_key

Removed value: -{
-  "description": "Optional secret desk_key. If provided, evaluates against your private criteria and saves evaluation to your scoreboard.",
-  "pattern": "^od_[0-9a-f]{32}$",
-  "type": "string"
-}

Changed1 schema field changedOct 5, 2026

removedOutput schema / properties / note_from_openkrill

Removed value: -{
-  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
-  "type": "string"
-}

Changed1 schema field changedOct 4, 2026

addedOutput schema / properties / note_from_openkrill

Added value: +{
+  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
+  "type": "string"
+}

First observedOct 4, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing state-dependent returns (status 'ready' with an empty form vs status 'ok' with evaluation plus three reply drafts) and the critical side effect that the evaluation is only persisted when the user has a desk — otherwise it scores against a sample profile and the agent must say so and offer set_criteria. That is exactly the kind of consequence disclosure the annotations (readOnlyHint=false only) do not provide.

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?

Five tight sentences, front-loaded with the routing decision before the return-value and side-effect details. Each sentence carries distinct operational information with no filler.

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

Completeness5/5

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

For a 5-param, mutating, state-dependent tool with nested file input, the description covers selection, both return modes, the persistence caveat, and the required user-facing follow-up. Even though an output schema exists, the extra context about the sample-profile fallback is what an agent needs to act correctly.

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 100%, so the schema already documents sender, channel, message, priority, and the file object including the 'Do not fill it yourself' note. The description reinforces that omitting message yields the empty form and that file input comes from an attachment, but adds no format or syntax detail beyond the schema — baseline 3 applies.

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?

States a specific function — the entry point for message intake that either opens the empty form or ingests an attached pitch file — and explicitly separates it from score_message for pasted pitches. An agent can pick between the two without opening either schema.

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?

Gives an explicit when-to-use ('only as the entry point... or when the user attaches a pitch file'), a when-not-to-use ('For a pitch pasted in chat, use score_message instead'), and an invocation constraint ('send no desk_key'). Nothing about selection is left to inference.

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

All Outreach Desk 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.