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

Adds real context beyond the annotations: the link must be handed to the user rather than opened, it is refused on MCP-key connections, and it is refused when no subscription exists. However, the annotations declare openWorldHint=true and readOnlyHint=false without the description clarifying why an external call is made or what the response payload looks like beyond the link, so the behavioral picture is strong on constraints but thin on the operation itself.

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?

Three short paragraphs, front-loaded with the outcome before the usage rules and eligibility caveats. Dense but each sentence carries a rule; the only slight cost is that the refusal conditions arrive late relative to the call conditions.

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 link generator with an output schema and annotations, the description covers the trigger, the prohibitions, the eligibility preconditions (signed-in payer, MCP-key refusal), and the fallback tool. An agent has everything needed to decide and call correctly.

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?

Zero parameters, so the schema has no semantics to convey and the baseline applies; the description correctly indicates the tool is scoped implicitly to the current workspace with no inputs needed. Nothing more is required here.

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 concrete artifact (a Stripe billing-portal link for the current workspace) plus exactly what the user does with it, and explicitly says it is not the place to describe plans or prices. It is cleanly separable from siblings get_subscription, get_plans, and subscribe.

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 an explicit trigger (user asks about plans, subscribing, or managing their subscription), an explicit prohibition (never volunteer, never suggest an upgrade elsewhere), and an explicit alternative (use subscribe when the workspace has no subscription). Nothing is left to inference.

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