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

Annotations already cover the read-only, non-destructive, closed-world profile, so the bar is lower, and the description still adds real behavior: OAuth requirement, a five-minute provider-refresh throttle, and the fact that the line is identical across devices. It doesn't explain error or not-found behavior, so not 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?

Four dense sentences with the core lookup and key constraint front-loaded; no wasted framing. A few phrases ('titular-owned', the parenthetical snapshot list) are slightly jargon-heavy but still informative.

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 two-parameter read tool with an output schema, this covers everything an agent needs: source of the ICCID, auth requirement, refresh semantics, and even a preview of the nested consumption payload. Nothing material is left out.

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% and both parameters are already documented, so the baseline is 3. The description echoes the refresh throttle and the ICCID provenance but adds no format or syntax detail the schema lacks.

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 (look up) and resource (remaining data for an eSIM line) keyed by ICCID, and explicitly anchors it to get_order_status as the upstream source. That anchoring distinguishes it from the sibling get_order_status and from the plan/order tools.

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 says where the ICCID must come from (a fulfilled get_order_status) and that OAuth is required, which is genuine usage context. It does not name an explicit when-not-to-use case or a competing alternative, so it stops short of a 5.

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