NUM Travel eSIM

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

Annotations already declare readOnlyHint and openWorldHint, so the bar is lower, but the description adds genuinely useful non-schema facts: prices are in USD, results are data-only with no phone number, and one plan is flagged as recommended. It does not say how many plans are returned or whether unavailable destinations yield an empty result.

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 short sentences, front-loaded with purpose and scope, then unit and content caveats. The only near-redundancy is 'Read only', which merely echoes the annotation, and it costs almost nothing.

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 three-parameter read-only lookup with no output schema, the description covers what the tool returns (plans plus a recommendation), currency, and the data-only limitation. It stops short of describing result shape or count, which would help an agent decide whether pagination or narrowing is needed.

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 the schema already documents destination examples and the use/days semantics (including the 14-day default), so the description adds essentially no per-parameter meaning. It only restates the destination forms in prose.

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 states a specific verb (find) and resource (NUM data eSIM plans) plus the accepted destination granularity, and the 'one recommended plan for the trip' clause distinguishes it from the checkout and order-status siblings, which cannot return a plan catalog.

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?

Usage is only implied: the mention of a recommended plan suggests this is the discovery step preceding esim_start_checkout, but the description never names that sibling or states prerequisites/exclusions. An agent must infer the browse-then-checkout workflow from the sibling names alone.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds genuine value with the negative contract 'Never returns an install code', which prevents a common wrong assumption about the response payload. It does not discuss polling cadence, error behavior for an unknown order_ref, or how long states take to transition.

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?

Two short sentences, zero filler, with the state list up front and the payload exclusion as a closing caveat. Every clause carries information the agent needs.

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 takes on the job of describing return values and does so by naming the four status values, plus flagging the install-code omission. It is slightly under-complete in that 'ready in NUM' is opaque and the broader response shape beyond status is unstated.

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?

There is a single parameter at 100% schema description coverage, so the baseline is 3. The description's mention that the order was started with esim_start_checkout echoes what the schema already states for order_ref, adding no new syntax, format, or sourcing detail.

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?

A specific verb (check) plus resource (order status) tied explicitly to the sibling that creates the order, esim_start_checkout. It goes further by enumerating the possible states (waiting for verification, waiting for payment, paid, ready in NUM), so an agent knows exactly what the tool reports and how it differs from esim_find_plans and esim_start_checkout.

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?

The description clearly anchors usage to orders already started via esim_start_checkout, which tells the agent this is a post-checkout tool and not a discovery tool. It lacks an explicit when-not statement or a pointer to whichever sibling would supply the install code it says it never returns, leaving that inference to the agent.

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

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

Beyond the annotations, it discloses key behavior: nothing is charged at this step, a checkout link is produced, the person must open it, confirm their number in NUM, and pay on Stripe themselves. This is exactly the operational context an agent needs before calling a non-read-only checkout-starting tool.

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 short, front-loaded with the core action, and every sentence carries useful information about the flow or the prerequisite. There is no 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?

There is no output schema, and the description compensates by explaining that the result is a checkout link and that payment occurs later on Stripe. Combined with the prerequisite and user-confirmation guidance, it gives enough context to call the tool correctly.

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%, so the schema already documents plan_id and destination with essentially the same guidance found in the description. The description does not add syntax, format, or edge-case meaning beyond the schema baseline.

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 uses a specific verb and resource: starting an order for a plan and obtaining a checkout link. It explicitly ties the plan to esim_find_plans, making its role distinguishable from that sibling tool.

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 clearly explains the prerequisite (a plan from esim_find_plans) and adds an explicit instruction to ask the person before calling. It does not name a when-not scenario or alternative beyond the prerequisite, so it falls short of the highest usage-guidance score.

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