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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real behavior beyond them: the 5-country cap, the default sizing rule (gb omitted = 1.5 GB/day from days), and the per-country output format with total. It doesn't discuss failures (e.g. an unsupported destination) or fallback when a country has no eSIM, which is why it isn't a 5.

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?

One dense paragraph, front-loaded with purpose, then the per-country day rule, then return shape, then routing to alternatives — a sensible order. Slightly redundant with the schema's own days description, and the parenthetical explanations stack up, but 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?

For a 7-param, 1-required tool with no output schema, the description covers the destinations, days, gb, per_country and return values adequately. The minor gaps are the locale params (bucket, currency, language) and no guidance on what happens when a destination in the list isn't sold — small omissions for a read-only quoting 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 coverage is 86%, so the baseline is 3, but the description earns more by hammering the most error-prone semantic: days is PER COUNTRY, never trip length, with a concrete worked example (12-day Japan+Thailand trip = 7 + 5). That's the exact misreading an agent would make from the schema alone. bucket and currency get no description treatment, capping it at 4.

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 ('a trip through several countries (max 5)'), the per-country quoting model, and the exact return shape (one line per country with price and buy_url, plus total). It explicitly separates itself from quote_esim (single country) and recommend_config (usage descriptions), so an agent can pick it without opening the 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?

Gives an explicit trigger ('when the customer names two or more countries and a size, 2–5 destinations') plus named alternatives with their selecting conditions: quote_esim for one country, recommend_config when they describe usage. Both when-to-use and when-not-to-use are covered.

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