FeedSquad

Get Brand Context

get_brand_context

Read-onlyIdempotent

Reads the user's confirmed business brain (Stash): voice and banned phrases, positioning, narrative beliefs and content pillars, audience ICP and pain points, person identity, brand basics. Returns only user-confirmed knowledge. Includes approved factual/opinion claims with source, approval/freshness dates, and linked proof IDs. These references do not include raw evidence. Approval of a claim is not consent to publish private or customer material; public-use permission is separate. The default concise format caps the example lists and returns the 10 most recently approved claims, with omitted saying how many were left out. response_format: "detailed" returns everything; sections limits the read to some sections. Banned phrases, the person identity, the usage notice and freshness dates are always returned.

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
`sections`	No	Sections to return; without it, every section.
`response_format`	No	concise (default) caps the example lists and returns the 10 most recently approved claims; detailed returns everything. Banned phrases, the person identity, the usage notice and freshness dates are always returned.

Output Schema

Name	Required	Description	Default
`kind`	Yes
`omitted`	No
`sections`	No
`brand_context`	No
`response_format`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, and the description goes well beyond that: it discloses that unconfirmed knowledge is excluded, that raw evidence is not included, that claim approval is not publication consent, that concise mode truncates example lists and caps at 10 recent claims with an omission count, and which fields are always returned. These are exactly the behavioral facts an agent needs before trusting the output for downstream publishing decisions.

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

Conciseness4/5

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

Dense and front-loaded: purpose and scope come first, then the consent caveat, then format behavior. It loses a little by repeating the response_format and always-returned wording that already appears verbatim in the schema, but every other sentence carries distinct information.

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?

An output schema exists, so the omission of return-structure detail is appropriate, and the description still covers what an agent most needs to know: truncation behavior, the fixed fields, the freshness/approval metadata, and the fact that claim approval is not public-use permission. Nothing essential for calling this safely is missing.

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 both parameters including the enum values and the always-returned set, and the description largely restates that. The one piece of added meaning is the note about the omission count in concise mode, which clarifies how truncation is signalled rather than how to set the parameter.

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?

Names a specific verb and resource ("Reads the user's confirmed business brain (Stash)") and immediately enumerates the content it holds: voice, banned phrases, positioning, narrative beliefs, pillars, ICP, person identity, brand basics. That enumeration distinguishes it clearly from get_brain_gaps (gaps) and tell_stash / propose_stash_items (writes), so an agent can pick it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by saying it returns only confirmed knowledge, which nudges an agent toward get_brain_gaps for missing knowledge, but never names a sibling or states prerequisites/exclusions explicitly. It does give clear guidance on which format to choose (concise default vs detailed) and how sections narrows the read, which is parameter-level rather than tool-selection guidance.

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

All FeedSquad 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?