Score an event

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

With no annotations, the description carries full weight and does an excellent job: it discloses monthly quota consumption, that it records an event, and the conditional identity block with email_canonical as a dedupe key. These are serious side effects an agent must know before invoking.

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?

Three sentences, perfectly front-loaded with the core purpose, then the email behavior, then the quota/recording warning. No wasted words or repetition of schema details.

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 tool with no output schema and no annotations, the description covers the essential return fields, side effects, and usage caveat. It lacks a full per-parameter breakdown, but the schema already lists all parameters and the description focuses on the most consequential behaviors.

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 only 29%, so the description must compensate. It adds meaningful semantics for "email" (identity block, dedupe key) and implicitly for "event" (the scoring trigger), but completely ignores ip, phone, user_id, and device_id—leaving those parameters opaque for the agent.

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 clearly states the tool's function: "Run an event through the scoring engine and get {score, verdict, reasons, checks}". It also distinguishes this from sibling check_* tools by focusing on scoring whole events and the added email identity dedupe feature.

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 explicitly advises "prefer the read-only tools when investigating history rather than testing new input", giving a clear alternative and context. It also notes the quota consumption and event recording, signaling this is for live scoring rather than historical investigation.

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