Reply to a Mattermost thread with a TL;DR summary of up to 5 lines, automatically finding the root message and checking channel membership before posting.
以 TL;DR 回覆討論串：最多 5 行、每行最多 50 字。postId 可為根訊息或既有回覆，會自動找出 root_id 並檢查頻道歸屬；非唯讀，須有使用者授權。
| Name | Required | Description | Default |
|---|---|---|---|
| postId | Yes | ||
| message | Yes | 請以 TL;DR 點出結論與重點。最多 5 行，每行最多 50 個 Unicode 字元；空白、標點、Markdown 與網址皆計數，空白行及結尾換行也計入行數。 | |
| channelId | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=false, so the sentence '非唯讀' earns no credit. Beyond them the description adds real behavior: the server auto-resolves root_id from either a root or a reply post, verifies channel membership, and requires user authorization — all non-obvious and useful. It stops short of saying what happens when the 5x50 limits are exceeded or what the call returns.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight, semicolon-joined clauses with no filler, and the output-format constraint is front-loaded where the agent will see it first. Slightly dense phrasing but nothing wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a non-idempotent write tool with no output schema, the definition covers format limits, ID resolution behavior, channel validation, and the authorization prerequisite — enough to call it correctly. The only real gap is failure behavior (limit violations, mismatched channel) and the shape of the response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 33%, with postId and channelId having no schema descriptions. The description compensates well for postId (accepts root or reply, root_id auto-resolved) and implicitly explains channelId's role via the 頻道歸屬 check. message constraints are fully covered by the schema already, so no further gain there.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb (回覆) and resource (討論串) plus the output format (TL;DR, 5 lines / 50 chars). An agent can distinguish it from mattermost_create_post by the thread-reply framing, but the description never names that sibling explicitly, so disambiguation is inferred rather than stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives useful preconditions — user authorization is required and postId may be either a root message or an existing reply — which tells the agent when this call is valid. However, there is no explicit when-not guidance and no named alternative (e.g. use create_post for a new top-level message), so routing between siblings is left implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.