Skip to main content
Glama

Create a tracked chat link

well_create_chat_invite_link

Make one tracked link to the WhatsApp chat with Well: a short Well link that opens the chat with prefill_text ready to send, followed by the link's reference code. Call it once per link the person asked for, such as one link per creator of a campaign or one per message variant.

Pass prefill_text exactly as the person wrote or approved it, or null for a link that opens the chat with the code alone. Well adds the code itself; never write a code into the text. Pass project_id of a campaign, or of one of its ad sets for one message variant, and person_id of the person the link is handed to, when the person named them.

The link opens until it is stopped with well_revoke_share_links. well_list_share_links lists it with how many people tapped it, how many conversations it started and how many of them signed up. Those are counts only: Well never tells the link's owner who tapped, wrote or signed up.

Give url to the person exactly as returned, on its own line, with one line that says it opens a WhatsApp chat with Well.

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
person_idNoThe person the link is handed to, such as a creator.
project_idNoA campaign, or one of its ad sets for one message variant.
prefill_textYesThe first message the chat opens with, as the person approved it; null for the code alone.
workspace_idNoTarget workspace. Omit when the token authorizes one workspace. Required when it authorizes several — a write lands in exactly one workspace and this call would not say 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.
idempotency_keyNoOptional client-supplied key. A retried write with the same key returns the original result instead of re-applying the operation.
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
urlNoThe link to hand out.
errorNo
successYes
ref_codeNoThe code the first message ends with.
person_idNo
project_idNo
prefill_textNo
share_link_idNo
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.
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. Added

TDQS

A3.9/5.0
Behavior1/5

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

The description discloses useful behavior beyond annotations, such as link lifetime, revocation, tweet counts, and the fact that Well does not reveal who tapped or signed up. However, it explicitly calls the operation 'this read' while the annotations set readOnlyHint=false for a creation tool. That directly contradicts the annotation that this is not a read-only operation.

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 description is front-loaded and organized around creation, parameter usage, lifecycle, and workspace scoping. It is fairly long, and some of the analytics and output-formatting detail could be trimmed, but most of it supports correct invocation.

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

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a seven-parameter create tool with an output schema, the description covers the essential behavior, lifecycle, and workspace scoping well. It omits explicit mention of conversation_id and idempotency_key, but the fully described schema carries those details.

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?

The schema already has full description coverage, so baseline semantics are strong. The description adds meaningful guidance for the most important parameters: prefill_text must be exact approved text or null, Well adds the code itself, project_id can be a campaign or ad set, and person_id is for the recipient. It does not add much for conversation_id, idempotency_key, or workspace_scope, but the schema covers those.

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 and resource: 'Make one tracked link to the WhatsApp chat with Well.' It clearly distinguishes the result from sibling behaviors by naming well_list_share_links and well_revoke_share_links, so the agent can tell what this tool creates and how it relates to adjacent tools.

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?

It gives explicit call guidance: call once per requested link, such as one per creator or one per message variant. It also explains when to pass project_id, person_id, and workspace_id, including the single-workspace versus multi-workspace distinction.

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