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

Beyond the readOnlyHint and openWorldHint annotations, the description richly discloses behavior: the per-day vs one-off pricing distinction, the volume discount up to 7 days, the dependence of price differences on routing_ip_country and networks, the grouping and sorting of results, and the return of variant_id for create_checkout. No contradiction with annotations.

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?

The description is long yet every sentence earns its place. It front-loads the core purpose and usage, then methodically covers pricing nuances, filters, pricing drivers, result ordering, and downstream integration. It is well-organized and dense with actionable information without fluff.

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?

Given the tool's complexity (7 params, no output schema, no nested objects), the description covers what an agent needs to call it correctly and interpret results: it explains the return value (variant_id), the grouping and sorting, how to pass parameters for accurate pricing, and how to use results for checkout. It also implies what fields might be useful for comparisons (routing_ip_country, networks). No significant gaps remain.

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%, but the description adds meaningful semantic context on top of the schema. For example, it explains that 'days' affects the total quote for unlimited plans and that 'unlimited' and 'min_data_gb' target different plan types. It also clarifies how to interpret prices across plan categories, which the schema alone does not convey.

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?

The description opens with a specific verb and resource: 'Search prepaid travel eSIM data plans for a destination.' It further clarifies the domain with 'SIM card / mobile data / roaming option for a trip' and positions itself as the entry point ('Use this first'). This clearly distinguishes it from siblings like find_cheapest_plan or get_plan_details.

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 explicitly states when to use: 'Use this first for any ... request.' It also explains what the tool includes (unlimited vs fixed-data) and how filters work. However, it does not explicitly exclude cases where alternatives like find_cheapest_plan or get_plan_details should be used instead, so it stops short of full guidance.

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