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

Adds substantial behavior beyond the annotations: asynchronous application of earning rules that may issue points/rewards, idempotency semantics (duplicate token+distinct_id is rejected), plan gating, and the required scope. The annotations only carry destructiveHint=true as a safety signal, so this extra context is genuinely valuable and does not contradict them.

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 a 'WRITE:' marker and packed with high-value constraints, but the many semicolon-joined clauses make it dense and slightly run-on compared to a tighter split into a purpose line plus a constraints line.

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?

Covers the write behavior, identity requirements, idempotency, plan and scope prerequisites, and the underlying endpoint. With no output schema, it does not state what the POST returns (e.g. activity id or resulting points), which is the one remaining gap for an agent that needs to chain calls.

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, but the description adds real meaning: token refers to a Smile Admin-configured activity type, distinct_id is the idempotency key (e.g. an order number), and the customer_id/customer_email pair is mutually exclusive with exactly one required. It also notes created_on_origin_at semantics implicitly via the backdating concept.

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 ('WRITE: record that a customer performed an action') and explains the token-based activity-type model. This is distinguishable from sibling writes like smile_create_points_transaction, which touches points directly rather than triggering earning rules.

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?

Gives concrete usage constraints: identify the customer by exactly one of customer_id or customer_email, pass distinct_id for idempotency, custom types require Plus/Enterprise, and the activity:write scope is required. It stops short of naming an explicit alternative sibling to use instead, so it is context-rich but not full routing.

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