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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds two pieces of context the agent cannot derive from them: that invoking it only mints a checkout link and no funds move until the user pays on Stripe, and that no confirmation step is required. It does not mention whether repeat calls create separate links (idempotentHint=false is declared) or any auth/rate considerations.

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 sentences, no filler, and the core action plus its most important consequence (no money moves yet) are front-loaded. The fallback-amount advice sits last where it belongs.

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 one-parameter tool with no output schema, the description covers what is produced (a checkout link), that it is a non-committal operation, and how to pick an amount. The only real gap is that it never says the returned link must be surfaced to the user for payment to complete, which the agent has to infer.

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% and the single parameter already documents USD units and the $5 minimum, so the baseline is 3. The description goes beyond the schema by telling the agent how to choose a value when the user gave none ($25, $50, $100, or enough to cover the planned send), which is real decision support rather than restatement.

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?

Specific verb and resource: 'Creates a Stripe checkout link to add funds to the user's Spur wallet', followed by what the wallet funds (postcards, letters, SMS, enrichment beyond plan). It implicitly separates itself from plan-related siblings by scoping to 'beyond the plan', but never names spur_manage_billing, spur_change_plan, or spur_set_auto_recharge, so sibling differentiation is left to inference.

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?

It gives a useful behavioral rule — 'no confirmation is needed' because no money moves until Stripe payment — and suggests default amounts when the user is vague. However, it never states when to pick this over spur_change_plan, spur_manage_billing, or spur_set_auto_recharge, which are the actual decision points an agent faces.

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