Mark

Get Brand Context

get_brand_context

Read-onlyIdempotent

Returns everything that shapes content: the Brand page's four sections (profile.voice, profile.visual, profile.overlay for entities and evidence, profile.offer for what is sold today, what is planned, pricing, promises and claims to avoid; profile.voiceError, visualError, overlayError or offerError explains a stored section that needs repair), personas (with wants, convincedBy, objections, pains, jobs and language: the customer's own words), pillars, angles, markets, buyer questions, KPI targets (for their actuals and progress, call get_content_performance), and active content exclusions. Call it before drafting or reviewing. brandReview says, per Brand section, whether a person has confirmed it (confirmed, confirmedAt) or it needs repair; tell the person which sections still need their review. claims lists the active claims (id, text, category, sourceQuote, sourceId, sourceTitle): the only checkable facts (numbers, prices, results, certifications) drafts may state. category is the workspace's own label. Retired claims are left out; for them and for search, call list_claims. sources lists the Claims & sources entries (id, title, url) that overlay evidence and claims cite by sourceId. profile.visual.logoAssetId is an asset id; call get_asset for the image. organizationJsonLd is the ready-to-paste Organization JSON-LD script built from the saved primary entity, company site, sameAs and Wikidata ids (null when there are no sameAs URLs or Wikidata ids), plus logo when the Brand logo was imported from a public URL (uploaded and Drive logos have no public URL, so logo is left out); it goes in the head of the person's home page. Personas, pillars, angles and markets include inactive rows (active: false). Each angle is one persona × pillar pair: it carries personaId and pillarId plus personaName and pillarName, so group angles by those to see which pairs have one. People edit personas, pillars and angles at /messaging, and markets at /markets. A market with null locationCode or languageCode has no search location, so AI search volume and answer-engine checks skip it. Does not change anything. Related: update_brand_profile, save_strategy_item, save_content_exclusion, list_claims, save_claim, get_channel_rules.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_brand_context"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description	Default
`angles`	Yes
`appUrl`	Yes
`claims`	Yes
`markets`	Yes
`pillars`	Yes
`profile`	Yes
`sources`	Yes
`personas`	Yes
`exclusions`	Yes
`kpiTargets`	Yes
`brandReview`	Yes
`buyerQuestions`	Yes
`organizationJsonLd`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 15, 2026

changedOutput schema / properties / brandReview / items / properties / section / enum

Previous value: -[
-  "voice",
-  "visual",
-  "overlay"
-]New value: +[
+  "voice",
+  "visual",
+  "overlay",
+  "offer"
+]

Changed3 schema fields changedOct 11, 2026

addedOutput schema / properties / claims / items / properties / sourceQuote
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / claims / items / properties / sourceTitle
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / properties / claims / items / required

Previous value: -[
-  "id",
-  "text",
-  "category",
-  "sourceId"
-]New value: +[
+  "id",
+  "text",
+  "category",
+  "sourceQuote",
+  "sourceId",
+  "sourceTitle"
+]

Changed2 schema fields changedOct 9, 2026

addedOutput schema / properties / organizationJsonLd

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "angles",
-  "appUrl",
-  "brandReview",
-  "buyerQuestions",
-  "claims",
-  "exclusions",
-  "kpiTargets",
-  "markets",
-  "personas",
-  "pillars",
-  "profile",
-  "sources"
-]New value: +[
+  "angles",
+  "appUrl",
+  "brandReview",
+  "buyerQuestions",
+  "claims",
+  "exclusions",
+  "kpiTargets",
+  "markets",
+  "organizationJsonLd",
+  "personas",
+  "pillars",
+  "profile",
+  "sources"
+]

Changed4 schema fields changedOct 8, 2026

addedOutput schema / properties / brandReview

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "appUrl": {
+        "type": "string"
+      },
+      "confirmed": {
+        "type": "boolean"
+      },
+      "confirmedAt": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "needsRepair": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "section": {
+        "enum": [
+          "voice",
+          "visual",
+          "overlay"
+        ],
+        "type": "string"
+      },
+      "title": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "appUrl",
+      "confirmed",
+      "confirmedAt",
+      "needsRepair",
+      "section",
+      "title"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / claims

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "category": {
+        "type": "string"
+      },
+      "id": {
+        "type": "string"
+      },
+      "sourceId": {
+        "type": "string"
+      },
+      "text": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "text",
+      "category",
+      "sourceId"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / sources

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "title": {
+        "type": "string"
+      },
+      "url": {
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "required": [
+      "id",
+      "title",
+      "url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / required

Previous value: -[
-  "angles",
-  "appUrl",
-  "buyerQuestions",
-  "exclusions",
-  "kpiTargets",
-  "markets",
-  "personas",
-  "pillars",
-  "profile"
-]New value: +[
+  "angles",
+  "appUrl",
+  "brandReview",
+  "buyerQuestions",
+  "claims",
+  "exclusions",
+  "kpiTargets",
+  "markets",
+  "personas",
+  "pillars",
+  "profile",
+  "sources"
+]

Changed2 schema fields changedOct 4, 2026

addedOutput schema / properties / exclusions

Added value: +{
+  "items": {},
+  "type": "array"
+}

changedOutput schema / required

Previous value: -[
-  "angles",
-  "appUrl",
-  "buyerQuestions",
-  "kpiTargets",
-  "markets",
-  "personas",
-  "pillars",
-  "profile"
-]New value: +[
+  "angles",
+  "appUrl",
+  "buyerQuestions",
+  "exclusions",
+  "kpiTargets",
+  "markets",
+  "personas",
+  "pillars",
+  "profile"
+]

First observedOct 1, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real substance beyond that: per-section error fields (profile.voiceError etc.) that signal a section needs repair, brandReview confirmed/confirmedAt state, inclusion of inactive rows (active: false), null locationCode/languageCode markets being skipped by AI search checks, and the conditions under which organizationJsonLd is null or omits logo. It stops short of describing response size or any pagination/truncation behavior, which matters for a context dump of this breadth.

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 content is valuable but delivered as one very dense block: the first sentence is a run-on with nested parentheticals enumerating four profile subsections and their error variants, and the organizationJsonLd explanation buries its key fact (null when no sameAs/Wikidata; no logo for uploaded/Drive) in a long aside. It is front-loaded in spirit but would be markedly easier to scan as short labeled segments.

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 zero-parameter context-fetch tool, the definition covers the full surface an agent needs: what each collection means, how to group angles, which rows are inactive, how claims relate to sources, when JSON-LD is absent or incomplete, and where humans perform edits. Nothing required to call or interpret it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. The extensive field-level explanation it does give (claims as 'the only checkable facts drafts may state', sources cited by sourceId, angles as persona × pillar pairs) is return-value semantics rather than parameter meaning.

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 opening sentence states a specific verb and resource ('Returns everything that shapes content') and then enumerates the concrete contents: brand profile sections, personas, pillars, angles, markets, buyer questions, KPI targets, exclusions. It also distinguishes overlaps with named siblings (retired claims and search go to list_claims; actuals go to get_content_performance), so an agent can tell it apart from get_workspace or get_channel_rules without opening a 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?

Usage is stated explicitly ('Call it before drafting or reviewing') and reinforced with routing rules for adjacent tools: get_content_performance for actuals, list_claims for retired claims and search, get_asset for logo images. It also names the human-facing edit surfaces (/messaging, /markets), which tells the agent this tool is read-only for those resources.

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

All Mark 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?