Skip to main content
Glama

Update Monitored Website

update_website
DestructiveIdempotent

Change a monitored website's display name, product description, or ignored keywords; omitted fields stay unchanged, and ignored terms hide matching mentions from scoring and lists.

Instructions

Update a monitored website's display name, description, or ignore list. Only the fields you pass change: omitted fields keep their value, and an empty description clears it. The description is the context the AI scores every new mention against, so keep it an accurate summary of the product; mentions already scored are not rescored. Use analyze_website to draft a description from the live site before saving it here. ignoredKeywords replaces the whole ignore list (the same list as the RedReplier app's ignore settings): any mention whose title or text contains one of these words or phrases, ignoring case, disappears from list_mentions and count_mentions, and new matches are hidden as they arrive. To add or remove one entry, read the current ignoredKeywords with get_website, edit that list, and send all of it back; [] clears the list and brings every hidden mention back. Confirm with the user before removing entries. URL and keywords cannot change through this tool: use add_keywords, edit_keyword, or disable_keyword for keywords. Returns the updated website with its ignoredKeywords and keyword list.

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": {
      "websiteId": "<websiteId>"
    },
    "name": "update_website"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoNew display name shown for the website in RedReplier, e.g. "Acme CRM". Omit to keep the current name unchanged
websiteIdYesID of the website to change, from list_websites or the id create_website returned
descriptionNoNew product summary that new mentions are scored against. An empty string clears it; omit to keep the current one
workspaceIdNoWorkspace to act in: an id from list_workspaces. Omit to use the default workspace. Use the same workspaceId for every call about the same workspace, since ids from one workspace do not exist in another
ignoredKeywordsNoWords or phrases whose mentions to hide, e.g. ["hiring", "job post"]. This becomes the whole ignore list, replacing the old one, so include every entry to keep. [] clears it; omit to keep the current list

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changedv1.6.0
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / description / description
      Previous value: -"New scoring context; an empty string clears it, omit to keep the current one"New value: +"New product summary that new mentions are scored against. An empty string clears it; omit to keep the current one"
    • addedInput schema / properties / ignoredKeywords
      Added value: +{
      +  "description": "Words or phrases whose mentions to hide, e.g. [\"hiring\", \"job post\"]. This becomes the whole ignore list, replacing the old one, so include every entry to keep. [] clears it; omit to keep the current list",
      +  "items": {
      +    "maxLength": 255,
      +    "type": "string"
      +  },
      +  "maxItems": 100,
      +  "type": "array"
      +}
    • changedInput schema / properties / name / description
      Previous value: -"New display name"New value: +"New display name shown for the website in RedReplier, e.g. \"Acme CRM\". Omit to keep the current name unchanged"
    • changedInput schema / properties / websiteId / description
      Previous value: -"Monitored website ID (UUID)"New value: +"ID of the website to change, from list_websites or the id create_website returned"
    • addedInput schema / properties / websiteId / format
      Added value: +"uuid"
    • addedInput schema / properties / workspaceId
      Added value: +{
      +  "description": "Workspace to act in: an id from list_workspaces. Omit to use the default workspace. Use the same workspaceId for every call about the same workspace, since ids from one workspace do not exist in another",
      +  "type": "string"
      +}
    • removedOutput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • addedOutput schema / properties / result / additionalProperties
      Added value: +true
    • removedOutput schema / properties / result / description
      Removed value: -"The updated website with its name, description, and keyword list."
    • addedOutput schema / properties / result / properties
      Added value: +{
      +  "accountGroupId": {
      +    "description": "Workspace the website belongs to",
      +    "type": "string"
      +  },
      +  "createdAt": {
      +    "description": "When the website was added, ISO 8601",
      +    "type": [
      +      "string",
      +      "null"
      +    ]
      +  },
      +  "description": {
      +    "description": "Context every new mention is scored against; null means new mentions go unscored",
      +    "type": [
      +      "string",
      +      "null"
      +    ]
      +  },
      +  "domain": {
      +    "description": "Domain taken from url; identifies the site in this account",
      +    "type": "string"
      +  },
      +  "id": {
      +    "description": "Website ID for the other tools",
      +    "type": "string"
      +  },
      +  "ignoredKeywords": {
      +    "description": "Lowercased words and phrases; mentions containing one are hidden",
      +    "items": {
      +      "type": "string"
      +    },
      +    "type": "array"
      +  },
      +  "keywords": {
      +    "description": "Every keyword on the website, in any status",
      +    "items": {
      +      "additionalProperties": true,
      +      "properties": {
      +        "createdAt": {
      +          "description": "When the keyword was added, ISO 8601",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "id": {
      +          "description": "Keyword ID for edit_keyword, enable_keyword, disable_keyword and delete_keyword",
      +          "type": "string"
      +        },
      +        "status": {
      +          "description": "PENDING (saved, not monitored until the plan covers it), ACTIVE, DISABLED or SUSPENDED",
      +          "type": "string"
      +        },
      +        "updatedAt": {
      +          "description": "When the keyword last changed, ISO 8601",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "value": {
      +          "description": "Lowercased keyword text, the value list_mentions filters on",
      +          "type": "string"
      +        },
      +        "websiteId": {
      +          "description": "Website this keyword belongs to",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "id",
      +        "websiteId",
      +        "value",
      +        "status",
      +        "createdAt",
      +        "updatedAt"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  "name": {
      +    "description": "Display name; null when none was set",
      +    "type": [
      +      "string",
      +      "null"
      +    ]
      +  },
      +  "updatedAt": {
      +    "description": "When the website last changed, ISO 8601",
      +    "type": [
      +      "string",
      +      "null"
      +    ]
      +  },
      +  "url": {
      +    "description": "Website address as saved",
      +    "type": "string"
      +  }
      +}
    • addedOutput schema / properties / result / required
      Added value: +[
      +  "id",
      +  "accountGroupId",
      +  "domain",
      +  "url",
      +  "name",
      +  "description",
      +  "ignoredKeywords",
      +  "createdAt",
      +  "updatedAt",
      +  "keywords"
      +]
    • addedOutput schema / properties / result / type
      Added value: +"object"
    • addedOutput schema / required
      Added value: +[
      +  "result"
      +]
  2. Changed2 schema fields changedv0.1.1
    • changedInput schema / properties / description / description
      Previous value: -"New description (used for relevance scoring)"New value: +"New scoring context; an empty string clears it, omit to keep the current one"
    • changedOutput schema / properties / result / description
      Previous value: -"The updated website record with its new name and description."New value: +"The updated website with its name, description, and keyword list."
  3. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=true, and the description earns credit by explaining the actual destruction semantics: ignoredKeywords replaces the entire list, [] wipes it and resurfaces hidden mentions, and removing entries should be user-confirmed. It further discloses that already-scored mentions are not rescored and that the return value is the updated website with its lists.

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-loads the mutable-field summary before the operational detail, and each subsequent sentence covers a distinct concern (patch semantics, scoring context, list replacement, restrictions, return value). The block is dense and could be split into short bullets, but little is wasted.

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 destructive partial-update tool with five parameters, the definition covers patch semantics, side effects on scoring, list replacement behavior, disallowed fields, prerequisites, and return shape. An agent has everything needed to call it without guessing.

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 baseline is 3, but the description adds consequences the schema does not: mentions already scored are not rescored when description changes, and clearing ignoredKeywords brings every hidden mention back. The replace-not-merge semantics of ignoredKeywords is somewhat redundant with the schema text.

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?

Opens with a specific verb and resource plus the exact mutable fields: "Update a monitored website's display name, description, or ignore list." It also draws a hard boundary against siblings by stating URL and keywords cannot change here and naming add_keywords, edit_keyword, and disable_keyword instead.

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?

Explicitly routes the agent: use analyze_website to draft a description before saving, use get_website to read current ignoredKeywords before editing, and use the keyword tools for keyword changes. It also adds a human-in-the-loop rule, "Confirm with the user before removing entries."

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