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

Annotations only cover safety/idempotency (readOnlyHint, idempotentHint, openWorldHint=false), so the description must carry the rest — and it does heavily: capability-level-only output, no price returned, provider/bank/acquirer anonymity enforced, economics as bands with no averaging/interpolation, and risk flags framed as generic readiness items rather than approval odds. This is unusually rich disclosure of output semantics and policy constraints.

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-loaded with purpose, trigger, and return content before the lengthy constraint block. The provider-anonymity and economics-band rules are restated in several forms ('never name, guess, hint at or confirm a provider...' and the closing provider/economics paragraph), adding redundancy, but each sentence is actionable for an agent.

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?

With 13 parameters, nested objects, no required fields and no output schema, the description does the needed work: explains what is returned, how partial input is handled (assumptions are surfaced), and the downstream handoff to design_stack. It does not indicate defaults or expected handling for empty/partial optional objects, which is the only real 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 coverage is only 46% across 13 nested parameters, so the description compensates by enumerating nearly all accepted inputs ('vertical or free-text description, plus any of jurisdiction, licences, monthly volume, average ticket, payment mix, consumer countries, settlement currencies, regions, current setup and treasury needs'). It also echoes the schema's vertical-vs-description dependency rule. It stops short of adding format/syntax meaning (e.g. currency units, percentage semantics) beyond parameter names.

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 ('takes a business profile ... returns what this business actually needs and why') and enumerates the concrete outputs (identified needs mapped to capabilities, assumptions, region rules, gaps). It also positions itself in the sibling set as 'the first substantive tool of the journey' and names design_stack as the next step, so an agent can distinguish it from recommend_stack or design_stack.

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 — 'call this whenever the user describes a business, a use case, a volume or a current payment setup' — and names the follow-on tool (design_stack for the full architecture). It does not state when *not* to use it versus list_solutions or compare_stack_scenarios, but the context is otherwise clear.

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