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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds useful behavioral context beyond that: it discloses the result shape ('the preferred unlimited offer or a few fixed bundles') and warns against inferring coverage from region names, which is a real matching-behavior caveat.

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 sentences, zero padding, with the core matching behavior front-loaded before the prerequisite and the exclusion. Every sentence carries actionable information.

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-parameter tool with 14% schema coverage and no output schema, the description is adequate but leaves gaps: it doesn't explain locale, minDataGb, or what happens when unlimited defaults to true and the bundles returned are fixed-data. The return shape is described only in loose qualitative terms.

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 only 14% (only 'days' is documented), so the description must compensate and does so partially: it explains that countryCodes must cover every requested country, that days/quantity/currency drive the result, and implicitly ties 'unlimited' to preferring unlimited offers. Undocumented are locale, minDataGb semantics, and the effect of unlimited's default of true versus fixed bundles.

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?

Uses a specific verb ('find') on a specific resource (unlimited offer or fixed bundles) and states the matching dimensions: all requested countries, duration, phone quantity, and payment currency. It is clearly distinguishable from siblings like list_esim_plans and compare_esim_prices because it describes a multi-constraint matching operation rather than a listing or price comparison.

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?

Explicitly routes the agent to search_esim_destinations as a prerequisite step ('resolve cities to country codes first') and adds a concrete exclusion ('Do not infer coverage from a region name'). It does not explain when to prefer this tool over compare_esim_prices or get_esim_upgrades, so it falls short of full when/when-not coverage.

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