@eqiqs/mcp-server

Official

by EQIQs

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

Write a coaching narrative

generate_narrative

Read-only

Creates a plain-language coaching narrative for one person or a pair, synthesizing 21 frameworks into work-safe behavioral insights.

Instructions

Premium: write a plain-language coaching narrative for one person, or for a pair when compare_with is given, synthesized from all 21 frameworks. Business context stays on working behavior only. Slower than other tools. Costs 5 units.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`focus`	No	Optional topic to emphasize, e.g. 'giving feedback'.
`length`	No	Approximate length of the narrative.	standard
`person`	Yes	Who the narrative is about. Accepts a profile id, an exact email, or a full name. If a name matches more than one person the tool asks which one instead of guessing.
`context`	No	Relationship context that sets framework weighting. 'business' (default) is work-safe and withholds personal-life signals (love language, attachment style, date of birth); the other contexts include them.	business
`audience`	No	Who will read it. Hiring or candidate-screening audiences are intentionally not supported.	manager
`compare_with`	No	Optional second person for a pair narrative. Accepts a profile id, an exact email, or a full name. If a name matches more than one person the tool asks which one instead of guessing.

Output Schema

TableJSON Schema

Name	Required	Description
`units`	No	Tool-call units this narrative costs.
`billing`	No	Units billed.
`context`	No	Relationship context for pair narratives.
`scoring`	No	Scores the narrative is based on.
`subject`	No	Person the narrative is about.
`audience`	No	Who the narrative is written for.
`sections`	No	Narrative split into sections.
`narrative`	No	The written coaching narrative.
`disclaimer`	No	Decision-support disclaimer.
`guardrails`	No	Safety check results.
`action_items`	No	Action items pulled from the narrative.
`compared_with`	No	Second person, for pair narratives.
`requires_confirmation`	No	True when the price must be confirmed before running.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.0.17Oct 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "action_items": {
+      "description": "Action items pulled from the narrative."
+    },
+    "audience": {
+      "description": "Who the narrative is written for.",
+      "type": "string"
+    },
+    "billing": {
+      "additionalProperties": {
+        "$ref": "#/properties/guardrails/additionalProperties"
+      },
+      "description": "Units billed.",
+      "type": "object"
+    },
+    "compared_with": {
+      "description": "Second person, for pair narratives.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "context": {
+      "description": "Relationship context for pair narratives.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "disclaimer": {
+      "description": "Decision-support disclaimer.",
+      "type": "string"
+    },
+    "guardrails": {
+      "additionalProperties": {},
+      "description": "Safety check results.",
+      "type": "object"
+    },
+    "narrative": {
+      "description": "The written coaching narrative.",
+      "type": "string"
+    },
+    "requires_confirmation": {
+      "description": "True when the price must be confirmed before running.",
+      "type": "boolean"
+    },
+    "scoring": {
+      "description": "Scores the narrative is based on."
+    },
+    "sections": {
+      "description": "Narrative split into sections."
+    },
+    "subject": {
+      "description": "Person the narrative is about.",
+      "type": "string"
+    },
+    "units": {
+      "description": "Tool-call units this narrative costs.",
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

Changed12 schema fields changedv0.1.1Sep 25, 2026

addedInput schema / properties / audience / default
```
Added value: +"manager"
```

changedInput schema / properties / audience / description

Previous value: -"Who the narrative is for. Hiring or candidate-screening audiences are intentionally not supported."New value: +"Who will read it. Hiring or candidate-screening audiences are intentionally not supported."

addedInput schema / properties / compare_with / description

Added value: +"Optional second person for a pair narrative. Accepts a profile id, an exact email, or a full name. If a name matches more than one person the tool asks which one instead of guessing."

addedInput schema / properties / context / default
```
Added value: +"business"
```

addedInput schema / properties / context / description

Added value: +"Relationship context that sets framework weighting. 'business' (default) is work-safe and withholds personal-life signals (love language, attachment style, date of birth); the other contexts include them."

addedInput schema / properties / context / enum

Added value: +[
+  "business",
+  "romantic",
+  "friendship",
+  "coparenting"
+]

addedInput schema / properties / focus / description

Added value: +"Optional topic to emphasize, e.g. 'giving feedback'."

addedInput schema / properties / focus / maxLength
```
Added value: +200
```
addedInput schema / properties / length / default
```
Added value: +"standard"
```

addedInput schema / properties / length / description

Added value: +"Approximate length of the narrative."

addedInput schema / properties / length / enum

Added value: +[
+  "short",
+  "standard",
+  "deep"
+]

addedInput schema / properties / person / description

Added value: +"Who the narrative is about. Accepts a profile id, an exact email, or a full name. If a name matches more than one person the tool asks which one instead of guessing."

First observedv0.1.0Sep 25, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare readOnlyHint/openWorld/destructive, and the description layers on non-obvious behavior: metered cost of 5 units, elevated latency, privacy weighting per context (business withholds love language, attachment style, DOB), and disambiguation behavior when a name matches multiple people. These are exactly the operational traits annotations cannot express.

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?

Three compact sentences, front-loaded with the premium/scope qualifier, then the privacy constraint, then cost and latency. Zero filler and nothing buried.

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?

An output schema exists, so return values need no explanation. For a 6-parameter tool with pair mode and context weighting, the description covers cost, latency, privacy behavior, and audience limits; the only thin spot is not restating accepted identifier forms, which the schema already handles.

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 every parameter including the context enum's withholding rules and the compare_with pair trigger. The description reinforces pair mode and framework synthesis but adds no format, syntax, or default semantics 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 verb (write) and resource (plain-language coaching narrative), names the person/pair scope modifier (compare_with), and identifies the synthesis source ('all 21 frameworks'). No sibling tool covers narrative generation, so the tool is unambiguously distinguishable from the rest of the set.

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?

Gives a clear trigger for pair mode ('when compare_with is given') and an explicit exclusion ('Hiring or candidate-screening audiences are intentionally not supported'), plus cost/speed signals ('Slower than other tools. Costs 5 units.') that steer an agent toward cheaper tools when adequate. It stops short of naming a specific alternative to use instead, so not a 5.

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

Deploy Server