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

Annotations already declare readOnlyHint=true, and the description reinforces it while adding genuine context: no usage is recorded and no send_event/lock behavior is exposed. It does not spell out the response shape (e.g. what allowed/balance fields come back) or error behavior, so it stops short of a 5.

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 tight sentences with the read-only guarantee and the endpoint front-loaded, followed by the negative-scope clarification. Nothing is wasted and nothing important 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 read-only check with no output schema, the description conveys the decision semantics (allowed vs. not enough balance, paywall preview via with_preview) well enough to call correctly. A brief return-value hint would close the remaining gap.

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% and every parameter is documented in-schema, including required_balance's default and with_preview's paywall purpose. The description adds only the loose 'enough balance of' phrasing, so the schema is doing the heavy lifting and baseline 3 applies.

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+resource ('READ-ONLY entitlement check: does a customer have access to ... a feature?') and pins the API operation (POST /v1/balances.check). The 'never records usage — does not expose send_event or lock' line cleanly separates it from the sibling that would do that (autumn_track_usage).

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 read-only/no-usage-recording framing makes the selection context clear: check access here, record consumption elsewhere. It stops short of naming autumn_track_usage explicitly as the alternative, so the routing is implied rather than stated.

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