supermetrics

manage_business_context

Destructive

Save or delete the durable business context a team applies consistently and shares with all members: reporting conventions, analysis rules, brand and tone, data governance, naming, plans, or account-specific preferences. Context is stored at team, data source, or account scope, chosen by ds_id/account_id.

save — Create/update at a scope; needs context_text and tags. Tags identify the entry within a scope, so a scope can hold several entries (one per tag set): mode: "replace" (default) overwrites the entry with those tags, mode: "append" concatenates to it, and a different tag set is saved as a separate entry rather than overwriting.
delete — Remove the single entry identified by scope (ds_id/account_id) and tags — it targets that one tag set, never the others at the scope. Omit tags to remove the untagged entry. Irreversible, so confirm first.

When to save: when the user shares a plan, guidelines, or an SOP; states a durable preference ("for this client, always…"); or corrects your approach — offer to save it so it applies in future sessions. Distill the key, reusable rules (do not store documents verbatim) and tag them by category (e.g. "data-analysis", "targeting", "naming-conventions", "brand-visuals", "brand-language"). Tags are how the entry is retrieved later, so avoid tags that merely restate the scope. Read the current context with get_business_context before changing it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "manage_business_context"
  }
}

Input Schema

Name	Required	Description
`mode`	No	'replace' (default) overwrites the entry with these tags; 'append' concatenates to it. A different tag set is saved as a separate entry
`tags`	No	Categories, comma-separated or JSON array. Tags identify the entry within a scope: required for 'save'. 'delete' targets the single entry with these tags
`ds_id`	No	Data source code (e.g. AW, FA); scopes to data-source level
`action`	Yes	save: create or update the entry; delete: remove it
`account_id`	No	Account ID; requires ds_id; scopes to account level
`context_text`	No	The context — guidelines, policies, or preferences, as plain text or JSON text. Required for 'save'. Up to 10,000 characters per entry; split larger material into separate tagged entries

Output Schema

Name	Required	Description	Default
`data`	No
`error`	No
`notes`	No
`success`	Yes
`business_context`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes further: it spells out that delete is irreversible and must be confirmed, that delete targets exactly one tag set and never the others at a scope, that omitting `tags` removes the untagged entry, and that replace/append differ in whether an existing entry is overwritten or concatenated. It also discloses the 10,000-character entry limit and the instruction to split larger material into separate tagged entries.

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?

Front-loaded with the resource and scope, then organized into per-action bullets and a bolded guidance block, so scanning is easy. It is on the longer side and repeats some content already present in the schema descriptions (mode semantics, tags-as-entry-identity), which costs a point but does not obscure the key facts.

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 6-parameter mutation tool with an output schema, the description covers scope resolution, entry identity via tags, action-specific requirements, irreversibility, size limits, and the read-before-write workflow. Nothing an agent needs to call this correctly — including how to avoid destroying sibling entries at the same scope — 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?

Schema coverage is 100%, so the schema baseline is already strong, yet the description adds operational meaning beyond it — notably that omitting `tags` on delete removes the untagged entry, and that a different tag set creates a separate entry rather than overwriting, which reframes what `tags` means as an entry identity key. It also gives tag examples ('data-analysis', 'targeting', 'naming-conventions') and warns against tags that merely restate the scope; the only minor gap is not restating the `account_id`-requires-`ds_id` dependency, which the schema covers.

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 opens with a specific verb pair and resource: 'Save or delete the durable business context a team applies consistently and shares with all members,' then enumerates the content types (reporting conventions, analysis rules, brand and tone, data governance, naming, plans, preferences). Each action is broken out with its own semantics, so an agent can distinguish save from delete and understand scope selection via `ds_id`/`account_id` 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 Guidelines5/5

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

There is an explicit 'When to save' block listing concrete triggers (user shares a plan/guidelines/SOP, states a durable preference, corrects your approach) plus an explicit precondition to 'Read the current context with `get_business_context` before changing it' — naming the read sibling directly. It also states when-not to store verbatim documents and requires confirmation before the irreversible delete.

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

All supermetrics 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?