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

Annotations only declare destructive/openWorld/non-idempotent; the description goes well beyond that by disclosing side effects the agent could not infer: the customer email becomes a lead if none exists, the lead's tags are merged, the server never subscribes anyone on its own, and an existing customer's stored subscription state may be replaced. That is exactly the mutation-impact context an agent needs before calling a destructive tool.

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-loads the write/side-effect warning and the endpoint (POST /orders) is a useful anchor. The consent guidance is spread across roughly three sentences that restate the same subscribed=true rule, which is mild redundancy rather than wasted space given the legal-weight of the point.

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 6-parameter, nested-object mutation with no output schema, the description covers the highest-risk semantics (lead creation, tag merge, subscription overwrite, no payment). It is silent on what the call returns and on what happens if an order_id is reused, which matters given idempotentHint=false.

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 83%, so the baseline is 3, and the description adds genuinely new meaning for `customer.subscribed` — that omitting it would default to true and that it can overwrite stored subscription state, which the schema field text does not state. Other parameters (order_id, currency, total_price, items) are 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 ('WRITE: record an order') and immediately scopes it by negating what the name might imply ('it does not take payment, charge a card or send email'). That negation distinguishes it from the sibling create_lead and from any actual payment tool, so an agent can route correctly without opening the schema.

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 clear operating context: this is a tracking record, and the `subscribed` flag must be passed explicitly with consent reasoning. It cross-references mailbluster_list_fields for merge tags. It does not, however, explicitly say when to use mailbluster_create_lead or mailbluster_create_product instead, so the sibling routing is left implicit.

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