get_channel_history

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

No annotations are provided, so the description carries the full behavioral burden — and it delivers. It discloses ordering semantics, the partial-inclusion of messages (thread replies excluded), the conditional return of reactions depending on bot scope, and failure modes the agent will encounter. This is exactly the behavioral context an agent needs beyond a bare 'get messages' statement.

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?

Four compact sentences that are front-loaded with the core purpose, followed by progressively specific usage details (diff fetching, thread exclusion, reactions scope, error conditions). There is minimal waste — every sentence earns its place. Slightly long compared to the simplest tools, but the richness matches the complexity of the behavior being disclosed.

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?

Given no output schema and no annotations, the description does an excellent job covering what an agent needs: retrieval semantics, incremental fetching, thread exclusion, reaction scope dependency, and error behavior. The only minor gap is that the exact response message structure isn't spelled out, though that's a conventional Slack message shape and the description notes reactions are included. Fully adequate for correct tool invocation.

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 100%, so the baseline is 3; the description raises it by adding real usage semantics for `oldest` — explaining that passing the previous ts yields only the diff. The ordering semantics ('新しい順') also clarifies how `limit` and `oldest` interact. `channelId` and `limit` are already well documented in the schema, so the description's marginal addition is meaningful but not extensive.

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-resource pair (get channel messages) with explicit ordering ('新しい順' = newest first). It clearly distinguishes itself from siblings by stating that thread replies are NOT included and routing messages with reply_count > 0 to get_thread_replies. An agent can reliably discriminate this from list_channels, list_active_threads, and get_thread_replies.

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 description provides explicit usage guidance: it explains the incremental-fetch pattern ('oldest に前回の ts を渡すと差分だけ取れる'), states when NOT to use it (thread replies require get_thread_replies), calls out the scope prerequisite (reactions:read for reactions), and discloses error conditions (not_in_channel / channel_not_found when bot not participating). This is model-grade routing and preconditions.

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