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

The description adds real context beyond annotations by disclosing the required 'billing' scope and that the output is a link handed to 'a person' — important for an agent to understand it should surface the URL rather than treat it as a direct action. It does not disclose the link's lifetime, whether it is single-use, or what the response shape looks like, and with readOnlyHint=false the mutation semantics of simply minting a link remain unstated. No contradiction with annotations.

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 short sentences: capability first, prerequisite second. No filler or repetition, though the phrasing 'a card subscription' is slightly loose and the prerequisite could be folded more tightly.

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 zero-parameter tool with no output schema, the description should state what comes back (a URL string) and whether the link expires or is single-use, since the agent must decide how to relay it. Those gaps matter more than they would if an output schema existed; the scope requirement is the one piece of missing context it does cover.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly says nothing about parameter syntax, and the implication that the target account is derived from the caller's authenticated context is left implicit.

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 names a concrete artifact (a billing portal link) and enumerates the three actions it enables: change card, view invoices, cancel a card subscription. It is distinguishable from most siblings such as quote_subscription or list_orders, though it does not explicitly contrast itself with cancel_subscription, the nearest overlap.

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?

Usage is implied by the enumerated actions, and the 'Needs the billing scope' prerequisite is genuinely useful for deciding whether the call will succeed. However, there is no explicit when-to-use/when-not guidance and no routing signal telling an agent to prefer cancel_subscription for a direct cancellation versus this link.

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