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

The description adds genuinely useful side-effect disclosure beyond the annotations: 'It starts or advances any active automation listening for that event,' which tells the agent this is not a passive log write. It stops short of explaining the destructiveHint=true claim, though — nothing says whether re-fires can re-trigger sequences or duplicate sends, which matters for a tool that initiates runs.

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?

Two sentences, front-loaded with the action and examples, then the consequence. Nothing is padded and nothing is buried.

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-parameter write tool with a nested properties object, no output schema, and destructiveHint=true, the definition covers purpose and side effect but omits the things an agent most needs: whether the call creates an unknown contact, what the response contains, and what 'destructive' means here.

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 60% — event, properties, and idempotency_key are documented in the schema, but phone and user_id carry no schema descriptions. The description partially compensates by indicating these are the identification pair ('and/or'), yet it never says whether supplying both is reconciled, which one is authoritative, or what happens if neither matches a known customer.

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?

Uses a specific verb ('Record') plus a concrete resource ('something a customer did') with three named example event names, so an agent immediately knows this is a customer-event ingestion call. It does not explicitly distinguish itself from nearby siblings like replay_event, simulate_inbound, or wait_for_events, which keeps it a notch below a 5.

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 phrase 'by user_id and/or phone' implies the identification context and tells the agent at least one identifier is expected. However, there is no statement of when to prefer this over replay_event or simulate_inbound, no prerequisites, and no guidance on which identifier wins when both are supplied.

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