Report Chat Message

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

Goes well beyond the annotations (which only say non-read-only, idempotent, non-destructive, open-world): one HTTP attempt, an immutable retained report snapshot, replay reusing that snapshot, the one-new-report-per-player-per-minute rate limit, no receipt history, and no implicit retry. The error semantics (404 masking, 409 conflict handling, 429 not scheduling retries, 501 no fallback) and the auth/key requirements are exactly the operational context an agent needs. No contradiction with idempotentHint=true, since same-original replay is described as reusing the retained report.

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?

Front-loaded with purpose and use-when, then requirement/side-effect/return/error blocks in a predictable order. It is dense and long, with minor duplication (HORIZON_API_KEY and 401 handling appear in both the requirements and errors sections), but almost every clause carries actionable information.

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 five-required-param mutation with no output schema, the description supplies the return shape ({reportId,status,replayed,serverTime}), auth prerequisites, side effects, idempotency semantics, and a full error-to-action mapping. Nothing an agent needs to call it correctly is missing.

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 adds real meaning: userId and sessionToken must come from a signin call's accessToken, and channelId/messageId must be the original canonical UUIDs that must never be replaced with unknown values. It does not add nuance on the 480-char reason cap beyond what the schema already states.

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 with scope: 'Reports one currently visible message with the original reason.' It also names the siblings it is not (horizon_get_chat_operation, horizon_send_chat_message), so an agent can route correctly. It stops short of 5 because the nature of a 'report' (moderation flag creating an immutable snapshot) only becomes clear later in the side-effects section rather than in the opening sentence.

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?

Explicitly gives when-to-use ('explicit hosted chat actions after reading horizon://docs/chat') and when-not ('automatic sends, repeated polling, rich-text rendering or exposing moderation credentials'). It then names the alternative tools and the exact ordering: reconcile with horizon_get_chat_operation, then horizon_send_chat_message only for an identical replay.

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