Well

Record mail offer

well_create_mail_offer

Record an unprompted offer to connect the mailbox, before the offer line is written. At most one offer per person and workspace every 24 hours, on every surface and across new conversations.

Call it once, before any text, when a skill is about to offer the mailbox without being asked. Write the offer only when it returns recorded: true. On recorded: false, an offer already went out in the last 24 hours: write no mail offer. A request the person makes ("connecte Gmail") is never an offer: do not call it then. It connects nothing and sends nothing. Say nothing about this call in the reply.

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

Name	Required	Description
`workspace_id`	No	Target 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_id`	No	The 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_key`	No	Optional client-supplied key. A retried write with the same key returns the original result instead of re-applying the operation.
`workspace_scope`	No	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.

Output Schema

Name	Required	Description
`error`	No
`success`	Yes	True when the call ran, whether or not the offer was recorded.
`recorded`	Yes	True when the offer is recorded now: write the mail line. False when one went out in the last 24 hours.
`next_offer_at`	No	When recorded is false, when the next offer is allowed.
`conversation_id`	No	The conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation.
`newly_connected`	No	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.
`conversation_id_note`	No	Present only when the server opened a fresh lane, stating that no choice recorded earlier was read.
`conversation_id_source`	No	Where 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.

Changed2 schema fields changedOct 28, 2026
- removedOutput schema / properties / next_offer_at / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / next_offer_at / type
```
Added value: +[
+  "string",
+  "null"
+]
```
AddedOct 19, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), it discloses the 24-hour per-person/per-workspace rate limit, that the call persists nothing but a bookkeeping record ('It connects nothing and sends nothing'), the required silence about the call in the reply, and the multi-workspace selection requirement. This is exactly the context annotations cannot carry.

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 critical rule (record once, before any text, only on recorded:true) is front-loaded. It is dense but every clause is operational; a few phrases, such as the workspace rationale, echo the schema and could be trimmed without loss.

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?

An output schema exists, yet the description still explains the meaning of recorded:true/false, which is the one output detail an agent must act on. Combined with the timing, rate-limit, and workspace rules, an agent has everything needed to call it correctly on the first try.

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?

With 100% schema coverage the baseline is 3, but the description adds actionable framing around workspace_id: call directly when the token authorizes one workspace, pass workspace_id when it authorizes several because 'this read will not guess which one you mean.' That restates the schema's intent in directive form, adding modest value rather than new information.

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 names a specific verb ('Record') and a precisely scoped resource ('an unprompted offer to connect the mailbox'), and draws a sharp line against related actions by stating that a user-requested connection ('connecte Gmail') is not this tool's concern. An agent can tell it apart from siblings like well_send_email_draft or well_get_mail_sender_choices without opening any 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?

It gives explicit timing ('Call it once, before any text'), an explicit exclusion ('A request the person makes is never an offer: do not call it then'), and an output-driven branch ('Write the offer only when it returns recorded: true'). Nothing about when to invoke or skip is left to inference.

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

All Well 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?