Fetches the page of stored messages before a specified message in a channel chat, so you can load earlier conversation history without starting a fetch.
A page of stored messages before a given one — never starts a fetch (POST /api/kalagh/messages/history · gRPC GetMessageHistory · socket "messages/history")
| Name | Required | Description | Default |
|---|---|---|---|
| chatId | Yes | ||
| channelId | Yes | ||
| messageId | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds two useful behavioral facts beyond the annotations: results are paginated ('a page') and directionally bounded ('before a given one'), plus the 'never starts a fetch' constraint on how it is invoked. It does not disclose ordering, page size, or termination behavior, so this is modest added value rather than rich context.
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?
A single front-loaded sentence states the purpose before the transport parenthetical, and there is no filler. The POST/gRPC/socket details are somewhat noisy for an agent choosing a tool, but they are compact and clearly bracketed.
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?
With no output schema, the description should carry more of the return-shape burden; it only says 'a page of stored messages.' Safety is covered by annotations and the pagination direction is conveyed, but the 0%-documented parameters and unspecified page semantics leave real gaps for a 3-parameter retrieval tool.
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 description coverage is 0% — the three properties carry only examples, no prose. The phrase 'before a given one' hints that messageId is the reference cursor, which partially documents one of three parameters, but chatId and channelId are left entirely unexplained in both schema and description.
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 names a concrete resource and scope — a page of stored messages positioned relative to a given message, i.e. backward pagination. This is more specific than a bare noun and lets an agent infer it is a history/cursor read, but it never names or distinguishes itself from siblings like messages_list, messages_get, or messages_search.
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?
The only usage hint is the parenthetical 'never starts a fetch,' which weakly implies this is for continuing backward through history rather than beginning one. There is no explicit when-to-use, when-not-to-use, or named alternative among the many message siblings, so an agent must guess when to prefer this over messages_list or messages_get.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.