Local MCP

Teams Send Message

teams_send_message

Destructive

Sends a text message to a Microsoft Teams chat as a connected Microsoft 365 work or school account (connect_m365_account), through Microsoft 365. The chat_id MUST come from teams_list_chats of the same account — never fabricate ids. This is a write operation: the first call returns a preview that says who is in the chat (or that they could not be read: chat_unresolved), the second call (with confirm=true) actually sends. Show the user those participants before confirming, above all when participants_state is not "resolved" or has_external_members is true. sent:true means Microsoft accepted the message; teams_search_messages reads Microsoft's search index, which can lag behind a send, so a zero-result search right after sending is NOT evidence the send failed.

Input Schema

Name	Required	Description
`text`	Yes	Plain-text message body. Max 28000 chars. No formatting / mentions / attachments.
`account`	No	Which connected Microsoft 365 account to use: its email (UPN), its id from list_m365_accounts, or its display name when unique. Leave it out to use the default account.
`chat_id`	Yes	Chat id from teams_list_chats (e.g. '19:<uuid>_<uuid>@unq.gbl.spaces' for 1:1, '19:<id>@thread.v2' for a group)
`confirm`	No	Must be true to actually send. Without it, returns a preview and sends nothing: the preview reads who is in the chat (`chat`: title, participants, participant_count, participants_state, has_external_members), or says chat_unresolved when that could not be read.
`remember`	No	With confirm: true, also stop asking for this kind of action from now on. Only when the person said so ("don't ask again"). The person can revoke it in LMCP or with set_always_allowed.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

addedInput schema / properties / remember

Added value: +{
+  "description": "With confirm: true, also stop asking for this kind of action from now on. Only when the person said so (\"don't ask again\"). The person can revoke it in LMCP or with set_always_allowed.",
+  "type": "boolean"
+}

Changed1 schema field changedOct 22, 2026

changedInput schema / properties / confirm / description

Previous value: -"Must be true to actually send. Without it, returns a preview without making any network call."New value: +"Must be true to actually send. Without it, returns a preview and sends nothing: the preview reads who is in the chat (`chat`: title, participants, participant_count, participants_state, has_external_members), or says chat_unresolved when that could not be read."

Changed3 schema fields changedOct 5, 2026

addedInput schema / properties / account

Added value: +{
+  "description": "Which connected Microsoft 365 account to use: its email (UPN), its id from list_m365_accounts, or its display name when unique. Leave it out to use the default account.",
+  "type": "string"
+}

changedInput schema / properties / chat_id / description

Previous value: -"Thread id from teams_list_chats (e.g. '19:<uuid>_<uuid>@unq.gbl.spaces' for 1:1, '19:<uuid>@thread.tacv2' for group)"New value: +"Chat id from teams_list_chats (e.g. '19:<uuid>_<uuid>@unq.gbl.spaces' for 1:1, '19:<id>@thread.v2' for a group)"

changedInput schema / properties / text / description

Previous value: -"Plain-text message body. Max 28000 chars. No formatting / mentions / attachments in v1."New value: +"Plain-text message body. Max 28000 chars. No formatting / mentions / attachments."

First observedJun 30, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses the two-step preview-then-confirm behavior, what the preview reveals (participants, participants_state, chat_unresolved), the guidance to show participants before confirming, and the meaning of sent:true. It also warns that teams_search_messages lags, so a zero-result search after sending is not evidence of failure — a genuinely useful non-obvious trait.

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 purpose, then the id-provenance constraint, then the confirm flow, then the search-lag caveat — a sensible priority order. It is dense and run-on in places (participants/sent semantics packed into long sentences), but nearly every clause carries actionable information.

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 write tool with an output schema present, the description supplies everything an agent needs: prerequisite id source, the preview/confirm contract, what the preview contains, safety guidance about revealing participants, and how to interpret sent:true. Nothing essential 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, but the description reinforces the critical constraint that chat_id must come from teams_list_chats and never be fabricated, and it explains the confirm gate's preview payload. That adds emphasis and meaning beyond 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?

States a specific verb and resource ('Sends a text message to a Microsoft Teams chat') plus the account scope (connected M365 work/school account via connect_m365_account). This clearly separates it from teams_send_channel_message and the other platform send_message siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly requires chat_id to originate from teams_list_chats of the same account and forbids fabricating ids, and it lays out the two-call preview/confirm sequence. It does not explicitly name teams_send_channel_message as the alternative for channel posts, so routing between chat vs. channel is only implied.

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

All Local MCP 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.