Skip to main content
Glama

Edit workspace

campaignstack_edit_workspace

Write workspace settings, branding, compliance, restore one playbook version, or accept/reject the pending playbook proposal. Only supplied components change. Branding affects client-facing shared artifacts only; compliance toggles the fixed lawful-basis notice; playbook restores are versioned. Read the pending proposal with campaignstack_get_workspaces' playbookProposal include before deciding it.

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": "campaignstack_edit_workspace"
  }
}

Input Schema

NameRequiredDescriptionDefault
brandingNo
settingsNo
complianceNo
workspaceIdNoWorkspace ID. Omit it when this connection reaches one workspace: a workspace key (cs_) is bound to its own, and a user key (csu_) or connected app whose person belongs to exactly one workspace defaults to that one. Required only when the person belongs to several; the error then lists them, and campaignstack_whoami reports them too.
proposalDecisionNo
restorePlaybookVersionIdNo

Output Schema

NameRequiredDescriptionDefault
okNo
resultsNo
warningsNo
workspaceIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / settings / properties / sections / description
      Previous value: -"The workspace playbook, one field per section. Only the fields you pass are changed. Each field has a target length and a HARD character cap; a write over the cap is REJECTED, not truncated. Write to the target, not the cap: identity (aim for about 400, max 1200, sent on every message): who we are, positioning, what makes us different; voice (aim for about 400, max 1200, sent on every message): rules that survive any voice: what to answer first, one ask per message, length caps. Never adjectives about tone, which get written into the drafts; angles (aim for about 1000, max 3000, sent on messages we send first): reasons to reach out that land, and the levers that persuade; objections (aim for about 2000, max 6000, sent on replies, after they have written back): what people push back with, and the real answers; boundaries (aim for about 500, max 1500, sent on every message): topics to avoid, claims never to make. Each section is model-facing text the model reads verbatim under its own heading: explanations of how the field works belong in the interface, not in the field, and a section must stand alone rather than refer to another one. Sections are selected per message, so a long objections list costs a first message nothing. Do NOT restate the offer, the personas or the campaign goal here: all three already reach the prompt from structured data, and a second copy can only contradict the first."New value: +"The workspace playbook, one field per section. Only the fields you pass are changed. Each field has a target length and a HARD character cap; a write over the cap is REJECTED, not truncated. Write to the target, not the cap: voice (aim for about 400, max 1200, sent on every message): rules that survive any voice: what to answer first, one ask per message. Never adjectives about tone, which get written into the drafts; angles (aim for about 1000, max 3000, sent on messages we send first): reasons to reach out that land, and the levers that persuade; objections (aim for about 2000, max 6000, sent on replies, after they have written back): what people push back with, and the real answers; boundaries (aim for about 500, max 1500, sent on every message): topics to avoid, claims never to make. Each section is model-facing text the model reads verbatim under its own heading: explanations of how the field works belong in the interface, not in the field, and a section must stand alone rather than refer to another one. Sections are selected per message, so a long objections list costs a first message nothing. Do NOT restate the offer, the personas or the campaign goal here: all three already reach the prompt from structured data, and a second copy can only contradict the first. Company facts (who we are, what we sell, proof, team) belong in the company profile, never in a section."
    • removedInput schema / properties / settings / properties / sections / properties / identity
      Removed value: -{
      -  "type": "string"
      -}
  2. Changed22 schema fields changed
    • changedInput schema / properties / settings / properties / companyProfile / description
      Previous value: -"The company facts the playbook asks for. null clears one."New value: +"A partial patch of the company profile, the labeled facts every message is grounded on. Only the fields you pass change; null (or an empty string or list) clears one. Each written field is recorded as stated by the user, so a website refresh never overwrites it. To move a fact out of offerContext into its field, pass the field here and the shortened offerContext in the same settings call: both land in one write, measured together against the company context limit."
    • addedInput schema / properties / settings / properties / companyProfile / properties / businessModel / description
      Added value: +"How it charges: subscription, usage-based, retainer, project, free."
    • addedInput schema / properties / settings / properties / companyProfile / properties / buyerAlternative
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "What the buyer does today instead. Read by playbook generation only, never sent."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / buyerRisk
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "What the buyer fears or what one mistake costs them. Read by playbook generation only, never sent."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / category
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "What kind of company it is, in a few words (also the workspace industry)."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / companyName
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The company's name."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / currentOffer
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The offer on the table now, its terms, and to whom."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / deliverables / description
      Added value: +"What can be offered or sent to a lead (a call, a teardown, a guide)."
    • addedInput schema / properties / settings / properties / companyProfile / properties / notFor
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Who should not buy, with the threshold."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / offer
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "maxLength": 500,
      +        "type": "string"
      +      },
      +      "maxItems": 50,
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The named things it sells, one short phrase each."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / positioning
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "How it differs from the alternatives, in one line."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / pricing
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "What it costs, as published."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / selfServe
      Added value: +{
      +  "description": "Whether a buyer can sign up without talking to anyone.",
      +  "type": [
      +    "boolean",
      +    "null"
      +  ]
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / stage
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The company's stage, e.g. pre-seed, bootstrapped, Series A."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / targetMarket
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Who it sells to."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / team
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Who is behind it and who is writing."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / traction
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "What can be proven (customers, named clients, results), or that there is none yet."
      +}
    • addedInput schema / properties / settings / properties / companyProfile / properties / whatWeAreNot / description
      Added value: +"What the company is not, so messages never claim it."
    • addedInput schema / properties / settings / properties / companyProfile / properties / whatWeDo / description
      Added value: +"What the company does."
    • addedInput schema / properties / settings / properties / companyProfile / properties / whyWeBuiltIt / description
      Added value: +"Why the founders built it."
    • addedInput schema / properties / settings / properties / companyProfileHidden
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Per-field switch: true keeps a stored field out of the company context sent with messages (for a fact offerContext already states), false puts it back. The value stays stored either way.",
      +  "properties": {
      +    "businessModel": {
      +      "type": "boolean"
      +    },
      +    "buyerAlternative": {
      +      "type": "boolean"
      +    },
      +    "buyerRisk": {
      +      "type": "boolean"
      +    },
      +    "category": {
      +      "type": "boolean"
      +    },
      +    "companyName": {
      +      "type": "boolean"
      +    },
      +    "currentOffer": {
      +      "type": "boolean"
      +    },
      +    "deliverables": {
      +      "type": "boolean"
      +    },
      +    "notFor": {
      +      "type": "boolean"
      +    },
      +    "offer": {
      +      "type": "boolean"
      +    },
      +    "positioning": {
      +      "type": "boolean"
      +    },
      +    "pricing": {
      +      "type": "boolean"
      +    },
      +    "selfServe": {
      +      "type": "boolean"
      +    },
      +    "stage": {
      +      "type": "boolean"
      +    },
      +    "targetMarket": {
      +      "type": "boolean"
      +    },
      +    "team": {
      +      "type": "boolean"
      +    },
      +    "traction": {
      +      "type": "boolean"
      +    },
      +    "whatWeAreNot": {
      +      "type": "boolean"
      +    },
      +    "whatWeDo": {
      +      "type": "boolean"
      +    },
      +    "whyWeBuiltIt": {
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / settings / properties / offerContext / description
      Added value: +"The user's own free text, read after the company profile fields; where the two disagree, this text wins. The whole company context (rendered fields plus this text) is capped at 2,500 characters; an over-cap write is rejected with GROUNDING_TOO_LONG. An empty string clears it."
  3. Changed1 schema field changed
    • addedInput schema / properties / settings / properties / companyProfile
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "The company facts the playbook asks for. null clears one.",
      +  "properties": {
      +    "businessModel": {
      +      "anyOf": [
      +        {
      +          "maxLength": 2000,
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "deliverables": {
      +      "anyOf": [
      +        {
      +          "maxLength": 2000,
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "whatWeAreNot": {
      +      "anyOf": [
      +        {
      +          "maxLength": 2000,
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "whatWeDo": {
      +      "anyOf": [
      +        {
      +          "maxLength": 2000,
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "whyWeBuiltIt": {
      +      "anyOf": [
      +        {
      +          "maxLength": 2000,
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
  4. Changed1 schema field changed
    • addedInput schema / properties / settings / properties / jevFeatures / properties / callbackTiming
      Added value: +{
      +  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
      +}
  5. Changed12 schema fields changed
    • changedInput schema / properties / settings / properties / jevFeatures / properties / agentGuard / $ref
      Previous value: -"#/properties/settings/properties/jevFeatures/properties/replyIntent"New value: +"#/properties/settings/properties/jevFeatures/properties/confidenceGate"
    • addedInput schema / properties / settings / properties / jevFeatures / properties / applicationPrefill
      Added value: +{
      +  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
      +}
    • changedInput schema / properties / settings / properties / jevFeatures / properties / briefIntent / $ref
      Previous value: -"#/properties/settings/properties/jevFeatures/properties/replyIntent"New value: +"#/properties/settings/properties/jevFeatures/properties/confidenceGate"
    • removedInput schema / properties / settings / properties / jevFeatures / properties / confidenceGate / $ref
      Removed value: -"#/properties/settings/properties/jevFeatures/properties/replyIntent"
    • addedInput schema / properties / settings / properties / jevFeatures / properties / confidenceGate / enum
      Added value: +[
      +  "off",
      +  "shadow",
      +  "live"
      +]
    • addedInput schema / properties / settings / properties / jevFeatures / properties / confidenceGate / type
      Added value: +"string"
    • removedInput schema / properties / settings / properties / jevFeatures / properties / critic
      Removed value: -{
      -  "$ref": "#/properties/settings/properties/jevFeatures/properties/replyIntent"
      -}
    • changedInput schema / properties / settings / properties / jevFeatures / properties / draftLabels / $ref
      Previous value: -"#/properties/settings/properties/jevFeatures/properties/replyIntent"New value: +"#/properties/settings/properties/jevFeatures/properties/confidenceGate"
    • addedInput schema / properties / settings / properties / jevFeatures / properties / memoryMatch
      Added value: +{
      +  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
      +}
    • addedInput schema / properties / settings / properties / jevFeatures / properties / profileMatch
      Added value: +{
      +  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
      +}
    • removedInput schema / properties / settings / properties / jevFeatures / properties / replyIntent
      Removed value: -{
      -  "enum": [
      -    "off",
      -    "shadow",
      -    "live"
      -  ],
      -  "type": "string"
      -}
    • addedInput schema / properties / settings / properties / jevFeatures / properties / replyRank
      Added value: +{
      +  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
      +}
  6. Changed1 schema field changed
    • changedInput schema / properties / workspaceId / description
      Previous value: -"Workspace ID. REQUIRED for a user key (csu_), which spans every workspace you belong to; omitted for a workspace key (cs_), which is bound to one and ignores this argument. campaignstack_whoami reports which kind of key you are holding and, for a user key, the workspaces it can reach."New value: +"Workspace ID. Omit it when this connection reaches one workspace: a workspace key (cs_) is bound to its own, and a user key (csu_) or connected app whose person belongs to exactly one workspace defaults to that one. Required only when the person belongs to several; the error then lists them, and campaignstack_whoami reports them too."
  7. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare the safety profile (not read-only, not destructive, not idempotent), and the description adds real substance on top: partial-patch semantics ("Only supplied components change"), the blast radius of branding (client-facing shared artifacts only), what compliance actually toggles (the fixed lawful-basis notice), and that restores are versioned. It stops short of explaining what happens when several modes are supplied in one call.

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?

The mode list is front-loaded in sentence one and each following sentence covers a distinct concern (patch semantics, per-component effects, the read-before-decide rule). Dense but no filler; only the final clause is slightly compressed for the amount of information it carries.

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

Completeness3/5

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 not be described, and annotations cover the safety profile. The remaining gap is mode interaction: for a six-parameter tool with several distinct write modes, the description never states whether proposalDecision can be combined with settings changes or whether the modes are mutually exclusive.

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 low at 17%, but the nested schema text itself is unusually rich (sections, companyProfile, offerContext, outreachIntents, companyProfileHidden, workspaceId all carry prose). The description adds effect-level meaning for branding, compliance, and restorePlaybookVersionId, but says nothing about settings, companyProfile, or outreachIntents beyond the generic "workspace settings" phrase.

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 names four concrete write modes (settings, branding, compliance, playbook version restore) plus a proposal accept/reject decision, all against a named resource (workspace). This clearly separates it from siblings like campaignstack_edit_workspace_members, campaignstack_edit_workspace_integrations, and campaignstack_propose_workspace_playbook_change.

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?

It gives an explicit prerequisite workflow: read the pending proposal via campaignstack_get_workspaces' playbookProposal include before deciding it, which is exactly the kind of routing an agent needs. It does not, however, say whether the modes are mutually exclusive or how to choose between editing settings here versus proposing a change via the sibling tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources