Skip to main content
Glama

Update a custom connector

well_update_custom_connector
Idempotent

Declare which tools of a server this workspace added (a custom connector) only read data. Well reads and syncs a tool only when it knows the tool changes nothing. Many servers do not say so for their tools, and then Well reads none of them until an owner or admin declares them here.

Call it only on the person's own ask, with the tool names exactly as well_list_connector_tools returned them. The list replaces the previous one. A tool the server itself marks as changing data is refused ("write_tools"), and a name the server does not list is refused ("unknown_tools"): nothing is saved then. Only a workspace owner or admin can declare; anyone else is refused.

Read outcome. "updated": say which tools Well now reads, by what they do. Any other outcome: say in one line why nothing was saved, and with "unknown_tools" or "write_tools" name the refused tools.

Input Schema

NameRequiredDescriptionDefault
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.
read_only_toolsYesEvery tool of this server the person declares read-only, by its exact name from well_list_connector_tools. The list replaces the previous one: a tool left out is no longer read-only, and an empty list declares none.
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.
workspace_connector_idYesThe custom connection's workspace_connector_id, from well_add_custom_connector or well_list_connectors.

Output Schema

NameRequiredDescriptionDefault
errorNo
toolsNoWith "unknown_tools" or "write_tools": the names that were refused.
outcomeNo"updated" when the list is saved. Otherwise why nothing was saved: "not_admin", "not_a_custom_connection" (the connection is not a server this workspace added), "too_many_tools", "tools_not_listed" (the server did not list its tools: it may need its sign-in first), "unknown_tools" (names the server does not list) or "write_tools" (tools the server itself marks as changing data).
successYes
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.
read_only_toolsNoThe tools now declared read-only.
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

A4.8/5.0
Behavior5/5

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

Adds substantial behavior beyond annotations: the list fully replaces the prior declaration (a tool left out stops being read-only), refusals are atomic ('nothing is saved then') with named error codes write_tools and unknown_tools, and permission gating. This is exactly the kind of mutation semantics annotations cannot convey, and it also explains the drop-on-omission risk despite destructiveHint=false.

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-loaded with the purpose and rationale, then constraints, then outcome handling; every paragraph carries information. The closing paragraph is somewhat instruction-heavy for response phrasing, but it earns its place given the outcome-dependent reporting requirement.

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 mutating, permission-gated tool, the description covers what changes, what is refused and why, who may call it, and how to report results; with an output schema and 100% schema coverage, nothing material is missing.

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 the baseline is 3; the description adds usable meaning on top, tying read_only_tools to exact names from well_list_connector_tools and explaining the refuse-on-unknown/write-tool behavior for those values, plus the replacement semantics. It does not touch workspace_id, conversation_id, idempotency_key, or workspace_scope, but those are fully documented in schema.

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?

States a specific verb and resource: declaring which tools of a custom connector are read-only, and explains the consequence (Well only reads/syncs tools it knows change nothing). This clearly separates it from well_list_connector_tools (which it references for names) and well_add_custom_connector, and corrects the vaguer 'update a custom connector' title.

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?

Explicit when-to-use constraint ('Call it only on the person's own ask'), a prerequisite for valid input (names exactly as well_list_connector_tools returned them), and an authorization condition (owner or admin only, others refused). Alternatives are routed to by naming the listing 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