Sync Chat Channel

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

Annotations only supply readOnly/openWorld/idempotent/destructive flags; the description adds substantial context beyond them: read-only POST with exactly one HTTP attempt, no retry scheduling on 429, cache-epoch validity rules, hide-on-disconnect/permission-change behavior, required HORIZON_API_KEY, and a mapping of 401/403/404/409/429/501 outcomes. Nothing contradicts the readOnlyHint=true annotation.

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?

The Use when / Not for / Requires / Side effects / Returns / Errors ordering is genuinely front-loaded and scannable, but the block is heavily over-long: error-code enumeration dominates and partially duplicates the usage section (repeated-polling prohibition appears twice, retry guidance repeats). Much of the density could be compressed without information loss.

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 5-required-parameter authenticated read with no output schema, the description covers prerequisites, auth wiring, return shape ({channel,visibleMessageIds,messages,moderation,serverTime}), cache consistency rules, and failure handling. An agent has everything needed to invoke and interpret it correctly.

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 100%, so the baseline is 3, but the description clarifies the semantics that the schema only hints at: sessionToken must be the accessToken from horizon_signin_email/horizon_signin_anonymous, userId must match the signed-in player, and known IDs are valid only for the exact cached epoch and a complete authorized cache. The epoch null-for-initial-sync case is left to the schema.

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?

States a specific verb and resource: reads an authorized incremental snapshot of a chat channel after a resync event or explicit user action. It differentiates from the send/reconcile siblings (horizon_get_chat_operation, horizon_send_chat_message) by name, but never distinguishes itself from the closest sibling, horizon_open_chat_channel, leaving the read-vs-open boundary implicit.

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?

Explicit 'Use when' and 'Not for' clauses name concrete triggers (after reading horizon://docs/chat, explicit hosted chat actions) and concrete exclusions (automatic sends, repeated polling, rich-text rendering, exposing moderation credentials). It also routes to the correct alternative tools for reconciliation and replay.

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