Skip to main content
Glama

Show a tool that is not available yet

well_show_connector_request
Read-only

Show the person a card for ONE tool Well cannot connect yet: the card names the tool, says where it stands in words (under maintenance, coming soon, not offered, or not in Well), and, except for a tool under maintenance, offers a request button, which asks Well to add it. Never name the button's label: the card writes it in the person's language.

Call it when the person names one tool to connect and a well_list_connectors read with that tool's slug (then q) returned no connectable row. Pass the name as the person wrote it, and the slug when a read returned one. Never offer another tool in its place, and never say Well refuses it.

When status comes back "ai_client_connects_itself", the tool is an AI app (Claude, Codex): nobody adds it to Well and no card or request exists for it. Answer in prose, in the person's language: the app connects to Well from its own settings, by adding Well's MCP server address (mcp_server_url, when set) there and signing in to Well. Never offer a request, the browser or Ajouter moi-même for it.

When status comes back "available", the tool can be connected now: draw the connect card with well_list_connectors and the slug of this result instead, and say nothing about a request. When connected is true, the workspace already holds a connection to the tool: no request card is drawn, so say in one line that it is already connected, and offer no request. When requested is true, say the workspace already asked for it.

When can_do_in_browser is true, the card also offers to do the person's task in the browser instead: its click comes back as the person's next message, and the connect-tools skill hands that task to the browser, starting on site_url when it is set. When it is false, never offer the browser in place of the tool.

When can_add_self is true, the card also offers "Ajouter moi-même": its click comes back as the person's next message, and the add-custom-connector skill adds the tool by the address of its MCP server. When it is false, never offer to add the tool oneself.

Write one line for the person, then stop: the card's button records the request and its click comes back as the person's next message. When no card is drawn and the person asks for the tool in words, call well_request_connector with the same name.

When the token authorizes one workspace, call this directly — no workspace call is needed first. When it authorizes several, this read will not guess which one you mean: pass workspace_id on the call.

Input Schema

NameRequiredDescriptionDefault
nameYesThe tool's name as the person wrote it, e.g. "Pipedrive". At most 60 characters: letters, digits, spaces and . & ' + -. Never an address, a link, an email or a domain suffix: write "Monday", not "Monday.com".
slugNoThe catalog slug, when a well_list_connectors read returned one for this tool. Omit otherwise.
workspace_idNoTarget workspace. Omit when the token authorizes one workspace. Required when it authorizes several: this read reports one workspace's own figures and will not choose which.
conversation_idNoThe conversation id returned by the previous Well result, in its meta under well/conversation_id, in its structuredContent, or in its JSON text block. Pass it back on every call in the same conversation, including a call a card makes, so the chosen workspace and the earlier answers still apply. It decides the conversation on its own: nothing the host states about the session replaces it. Omit it only on the first call of a conversation.
workspace_scopeNoRestrict this call to the family: the token's primary workspace plus the company workspaces under it that you are a member of. Unrelated authorized workspaces drop out of the read; row reads merge across the family, while a per-workspace figure still reports exactly one workspace.

Output Schema

NameRequiredDescriptionDefault
nameNoThe tool's name in a form well_request_connector accepts: the catalog name, cleaned, when the catalog carries it. Pass it back unchanged to request the tool.
slugNoThe catalog slug of the matched tool, or null when it has none or the catalog does not carry the tool. Pass it as `slug` to well_list_connectors when status is available.
errorNo
statusNoWhere the tool stands: "maintenance" (Well carries it and it is under maintenance: the card offers no request), "coming_soon", "not_offered", "absent" (not in Well), "available" (connectable now: draw the connect card instead), or "ai_client_connects_itself" (an AI app such as Claude or Codex: no card, no request; answer in prose that it connects from its own settings with `mcp_server_url`).
successYes
site_urlNoThe https home of the tool's site, from the catalog, or null when the catalog names none. A browser task for this tool may start there.
connectedNoTrue when this workspace already holds a live connection to the tool, whatever the catalog says. No request card is drawn.
requestedNoTrue when this workspace already asked for the tool.
service_idNoThe catalog service id, or null for a tool the catalog does not carry.
request_keyNoThe key Well records a request for this tool under. Well reads it; never pass it to a tool.
can_add_selfNoTrue when this person can add the tool themselves as a custom connector: an admin, in a real workspace, in a turn that can run the custom-connect write. The card shows Ajouter moi-même only then.
mcp_server_urlNoOnly when status is "ai_client_connects_itself": Well's MCP server address, which the person adds in the AI app's own settings to connect it to Well. Null when the address is unknown.
conversation_idNoThe conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation.
newly_connectedNoTools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. The connected-line rule says when to tell an entry; when it does, one line per entry, in the person's language: "<name> is connected.". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later.
can_do_in_browserNoTrue when this turn can hand the person's task to a browser instead (their Chrome with the Well extension when it can take it, a Well cloud browser otherwise). The card then offers to do the task in the browser; its pick comes back as the person's next message.
resolved_workspaceNoThe workspace that answered, when the caller named none and the token authorizes several.
conversation_id_noteNoPresent only when the server opened a fresh lane, stating that no choice recorded earlier was read.
conversation_id_sourceNoWhere the conversation id came from: the host's own request meta, the caller's argument, or a fresh lane the server opened.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedOutput schema / properties / mcp_server_url
      Added value: +{
      +  "description": "Only when status is \"ai_client_connects_itself\": Well's MCP server address, which the person adds in the AI app's own settings to connect it to Well. Null when the address is unknown.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / status / description
      Previous value: -"Where the tool stands: \"maintenance\" (Well carries it and it is under maintenance: the card offers no request), \"coming_soon\", \"not_offered\", \"absent\" (not in Well), or \"available\" (connectable now: draw the connect card instead)."New value: +"Where the tool stands: \"maintenance\" (Well carries it and it is under maintenance: the card offers no request), \"coming_soon\", \"not_offered\", \"absent\" (not in Well), \"available\" (connectable now: draw the connect card instead), or \"ai_client_connects_itself\" (an AI app such as Claude or Codex: no card, no request; answer in prose that it connects from its own settings with `mcp_server_url`)."
    • changedOutput schema / properties / status / enum
      Previous value: -[
      -  "available",
      -  "maintenance",
      -  "coming_soon",
      -  "not_offered",
      -  "absent"
      -]New value: +[
      +  "available",
      +  "maintenance",
      +  "coming_soon",
      +  "not_offered",
      +  "absent",
      +  "ai_client_connects_itself"
      +]
  2. Changed8 schema fields changed
    • removedOutput schema / properties / resolved_workspace / properties / name / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / resolved_workspace / properties / name / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / service_id / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / service_id / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / site_url / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / site_url / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / slug / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / slug / type
      Added value: +[
      +  "string",
      +  "null"
      +]
  3. Changed2 schema fields changed
    • addedOutput schema / properties / can_do_in_browser
      Added value: +{
      +  "description": "True when this turn can hand the person's task to a browser instead (their Chrome with the Well extension when it can take it, a Well cloud browser otherwise). The card then offers to do the task in the browser; its pick comes back as the person's next message.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / site_url
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The https home of the tool's site, from the catalog, or null when the catalog names none. A browser task for this tool may start there."
      +}
  4. Changed1 schema field changed
    • changedOutput schema / properties / newly_connected / description
      Previous value: -"Tools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. Start the reply with one line per entry, in the person's language: \"<name> is connected.\". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later."New value: +"Tools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. The connected-line rule says when to tell an entry; when it does, one line per entry, in the person's language: \"<name> is connected.\". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later."
  5. Changed4 schema fields changed
    • addedInput schema / properties / workspace_scope
      Added value: +{
      +  "description": "Restrict this call to the family: the token's primary workspace plus the company workspaces under it that you are a member of. Unrelated authorized workspaces drop out of the read; row reads merge across the family, while a per-workspace figure still reports exactly one workspace.",
      +  "enum": [
      +    "family"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / request_key
      Added value: +{
      +  "description": "The key Well records a request for this tool under. Well reads it; never pass it to a tool.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / status / description
      Previous value: -"Where the tool stands: \"coming_soon\", \"not_offered\", \"absent\" (not in Well), or \"available\" (connectable now: draw the connect card instead)."New value: +"Where the tool stands: \"maintenance\" (Well carries it and it is under maintenance: the card offers no request), \"coming_soon\", \"not_offered\", \"absent\" (not in Well), or \"available\" (connectable now: draw the connect card instead)."
    • changedOutput schema / properties / status / enum
      Previous value: -[
      -  "available",
      -  "coming_soon",
      -  "not_offered",
      -  "absent"
      -]New value: +[
      +  "available",
      +  "maintenance",
      +  "coming_soon",
      +  "not_offered",
      +  "absent"
      +]
  6. Changed1 schema field changed
    • addedOutput schema / properties / newly_connected
      Added value: +{
      +  "description": "Tools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. Start the reply with one line per entry, in the person's language: \"<name> is connected.\". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "name": {
      +        "type": "string"
      +      },
      +      "service_id": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "name",
      +      "service_id"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  7. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say readOnlyHint=true, which the description is consistent with — the card's button records the request and its click returns as the person's next message, so the tool itself performs a read. Beyond that, the description discloses the full branch table of returned statuses (ai_client_connects_itself, available, connected, requested) and what to do in each, plus can_do_in_browser and can_add_self gating and the multi-workspace requirement for workspace_id.

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 core purpose and trigger are front-loaded, and the branching status cases are organized sequentially with no filler. It is long — roughly ten sentences of conditional policy — but nearly every sentence carries a distinct behavioral rule an agent would otherwise get wrong.

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 card-rendering tool with conditional follow-up actions, the description covers invocation conditions, all response states, the fallback tool, workspace scoping, and even output formatting constraints ("write one line for the person, then stop"). Combined with an existing output schema and read-only annotations, nothing needed to invoke it correctly 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 coverage is 100%, so every parameter is already documented, including the exact rules for `name` formatting and the workspace_id multi-workspace condition. The description largely restates these ("pass the name as the person wrote it, and the slug when a read returned one") rather than adding new meaning, so the baseline of 3 applies.

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 first sentence names a specific verb and resource — "Show the person a card for ONE tool Well cannot connect yet" — and scopes it to exactly one tool. It is immediately distinguishable from well_list_connectors (which finds connectable rows) and well_request_connector (the fallback when no card is drawn).

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?

The trigger is stated as a concrete precondition: call it when the person names one tool and a well_list_connectors read with that slug (then q) returned no connectable row. It also names the alternative for the no-card case ("call well_request_connector with the same name") and the case where status is "available" (go back to well_list_connectors), plus explicit negations: "Never offer another tool in its place" and "never offer a request" for ai_client_connects_itself.

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