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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the marginal bar is low, and the description still adds real behavior: output is ordered ascending by fee, and banks with no published fee or no such service are sorted last with an explanatory reason. That edge-case handling is not derivable from annotations or schema.

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 tight sentences: what it produces, how to scope the call, and how non-qualifying banks are handled. The ranking direction is front-loaded, and no sentence is filler.

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 no output schema, the description carries the burden of describing returns, and it does cover ordering and the 'listed last with reason' case. It leaves unspecified whether fee amounts, effective dates, or source citations come back per bank — a small but real gap for a comparison tool.

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 both enums are self-describing, so the baseline is 3. The description paraphrases the enum axes in natural language ('in dollars or foreign currency', 'personal or business') and restates the 2–17/omit rule, which is helpful framing but largely repeats structured data.

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 and resource — 'ranks US banks from lowest to highest published fee' — and pins the scope to one wire type across four axes (direction, domestic/international, currency, account type). The multi-bank ranking framing also implicitly separates it from get_bank_wire_fees (single bank) without opening either schema.

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?

'Pass 2 to 17 banks, or none to rank every bank covered' gives explicit invocation context, including the omit-to-broaden behavior. It stops short of naming alternatives like find_cheapest_way_to_send_money, so the agent must infer the boundary between ranking fees and computing total send cost.

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