Slashtel

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds meaningful context beyond that: the dual-key requirement, the constraint that both identifiers must match the same order, and the enumeration of possible status values.

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?

Front-loaded with what it returns, followed by requirements and usage triggers. The parenthetical explaining ICCID is slightly verbose but earns its place by helping an agent locate the value; overall efficient with 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?

With no output schema, the description carries the return-value burden and does so by listing all returned fields and status values. It omits error behavior (e.g. what happens when identifiers don't match an order), which is a minor gap for a lookup 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 100%, so baseline is 3, but the description adds real meaning: ICCID format (long number starting 89, found in order email and phone settings) and that the email must be the one used at checkout. It also explains the cross-parameter constraint that both must belong to the same order.

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+resource (check eSIM status) and enumerates exactly what is returned: data used/left, plan size, expiry, status values, and auto top-up state. This is clearly distinguishable from siblings like check_phone_compatibility or get_esim_plans.

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 explicit trigger scenarios ('how much data they have left or why their eSIM stopped working') and prerequisites (email AND ICCID must match the same order). It does not name alternative tools or state when NOT to use it, so it falls 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.

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond that: it explains the tool returns step-by-step instructions (iPhone and Android variants), that the brand argument switches to brand-specific steps, and why the check matters for installation success.

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 front-loaded sentences with no filler: purpose, parameter effect, then usage trigger. The final sentence is somewhat long, but every clause carries decision-relevant information for the agent.

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 single-optional-parameter, no-output-schema guidance tool, the description covers what it does, what it returns in human terms, when to call it, and why it matters. Nothing needed to invoke it correctly is missing.

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 baseline is 3, but the description adds the consequence of supplying the optional argument ('brand-specific steps'), which is more than the schema's plain example list conveys. It also clarifies the parameter is optional, matching required=0.

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 action on a specific subject: it explains how a traveller verifies their phone supports eSIM and is unlocked, returning step-by-step guidance. This is clearly distinct from siblings like check_esim_status (which checks an existing eSIM's state) and create_checkout_link.

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 names the when ('before create_checkout_link when the user is unsure their phone will work') and gives the reason ('an incompatible or locked phone is the most common reason an eSIM cannot be installed'). That is both a trigger condition and an alternative-tool reference.

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, idempotentHint=true, and non-destructive, which are consistent with generating a link rather than creating a server-side record. The description adds real behavioral context beyond annotations: the payment happens off-platform and the link is meant to be shared with the user.

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 tightly written sentences, front-loaded with the outcome (a link), then the user flow, then the parameter branching. 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?

With no output schema, the description correctly states what is returned (a link URL) and how the consumer uses it. It covers the composite parameter requirements for both enum branches. Minor gap: no mention of error/failure behavior, but otherwise complete for the task.

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 80%, but the description adds the key conditional logic the schema cannot express — which parameters to pass based on the 'type' enum value. That mapping (esim→plan_id; topup→phone/operator_code/send_value) is genuine value beyond the field descriptions.

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 (returns a slashtel.com link) with the scope of what's pre-selected (eSIM plan or top-up). The mention of get_topup_plans and get_esim_plans implicitly distinguishes it from the plan-listing siblings, so an agent can tell it isn't a lookup 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?

Gives explicit workflow guidance — share the link, user enters email and pays on site — and branches by type ('esim' → plan_id; 'topup' → phone, operator_code, send_value). It lacks explicit when-not-to-use conditions, but the conditional parameter routing is strong usage guidance.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful context beyond that: nothing is actually created server-side until the traveller confirms on the external site, which resolves the tension between the 'create_' name and the read-only hint. It does not mention link expiry, but that is a minor omission given the annotation coverage.

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, front-loaded with what the tool returns, followed by the user-confirmation flow. Every sentence carries distinct information and 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?

With only five flat parameters, no output schema, and full annotation coverage, the description covers what an agent needs: the return value (a link), the target site, and the confirmation flow that explains why a 'create' tool is read-only. Minor gap: no mention of whether the link has a lifetime or whether origin_name/destination_name affect the output.

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 100%, so origin, destination, month, and the two city-name fields are already documented in the schema. The description only confirms that the route is pre-filled, adding no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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: it 'Returns a slashtel.com link that opens the free flight price alert form with the route filled in.' The agent knows exactly what comes back and what the link does. It doesn't explicitly contrast with the sibling create_checkout_link, which also produces a link, so it falls short of full sibling differentiation.

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 implied by the flow described (traveller confirms their own email on the site), but there is no explicit 'use this when' guidance and no exclusion naming create_checkout_link or get_flight_fares as the alternative. The agent must infer the selection criteria from context.

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, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds non-annotation context: results are 'live' (current pricing), priced in USD, and normalize to a price-per-GB figure. It stops short of describing pagination or result limits.

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 tight sentences with no filler: the first front-loads what is returned, the second covers the required destination format and optional filters. Every clause earns its place.

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 carries the return-shape burden and does so by naming the four returned attributes. Combined with the 100%-covered input schema and explicit code-source guidance, an agent has everything needed to call this 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 description coverage is 100%, so the schema already documents all three parameters, giving a baseline of 3. The description adds mild value by clarifying that destination accepts an ISO-2 code or a code from list_esim_destinations and that min_gb/min_days narrow the list, but this largely restates the schema.

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 (live travel eSIM plans for one destination) and enumerates the returned fields: data GB, validity days, price USD, price per GB. It distinguishes itself from list_esim_destinations by referencing it as a code source, but does not explicitly differentiate from the sibling get_topup_plans.

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 concrete usage guidance: supply an ISO-2 country code (with examples TR, JP, US, GB) or a destination code obtained from list_esim_destinations, and notes the filters are optional narrowing. No explicit when-not-to-use or alternative-selection rule, but the context is clear.

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 readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered; the description adds genuinely new context beyond that — fares are cached, quoted in GBP while the airline bills in its own currency, and Slashtel is not a seller. It also discloses the 12-vs-3-month coverage ceiling and that a citable source page is included. Freshness/staleness of the cache and failure behavior are the only notable omissions.

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?

Content is front-loaded: what is returned comes first, then input format, then the currency/seller caveat. The sentences are long and clause-heavy, but each carries distinct information (return fields, coverage window, currency caveat, citation source) rather than 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?

With only two required parameters and no output schema, the description does the work of describing the response shape (price, airline, stops, cheapest month, source page) plus currency and coverage caveats, which is nearly everything needed to call and interpret the tool. Only error/no-route handling and result ordering are left 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?

Schema description coverage is 100% and both parameters are already documented as 'IATA airport or city code' with examples. The description reinforces that city codes are acceptable (LON, DEL, DXB, NYC, YTO, MNL), which is a marginal restatement rather than adding format rules, validation constraints, or case-sensitivity guidance. Baseline 3 applies.

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 ('Cheapest one-way fares by month for a route') and enumerates exactly what is returned: price, airline, stops per month plus the cheapest month. An agent can immediately tell this is a monthly fare-lookup tool, and nothing in the sibling list (eSIM, top-up, checkout, price alerts) overlaps with it.

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 implied by the framing rather than stated: the description explains coverage depth differs between tracked routes (12 months) and any other route (3 months), which is a useful condition for interpreting results. However it never says when to prefer this over a price-alert or checkout flow, nor what to do if a route is untracked or codes are invalid, leaving prerequisites to inference.

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 readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds substantive behavior the annotations do not: the payload fields returned (airports, scheduled vs expected times, terminal, gate, baggage belt, in-air flag, last reported position) and the live-tracking/alert side effect. Minor gap: no mention of behavior for an unknown or ambiguous flight number.

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 first sentence is a long undifferentiated list of returned fields, and the closing clause about a slashtel.com link and free email alerts reads as promotion rather than information an agent needs to select or invoke the tool. The usage sentence is front-loaded well, but roughly a third of the text does not earn its place.

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 carries the return-shape burden and does so well by enumerating the key fields. For a two-parameter read tool with full annotation coverage, that is nearly complete; only error/not-found behavior 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?

Schema coverage is 100%, so both parameters are already fully documented including the enum and the departure-airport-local-time nuance. The description only restates the yesterday/today/tomorrow window and adds no format or disambiguation guidance beyond the schema; baseline 3 applies.

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 names a specific verb and resource ("Live status of a flight by its number") and bounds the scope to yesterday/today/tomorrow, so an agent knows exactly what it retrieves. It does not differentiate from sibling tools, though the siblings (eSIM, top-up, price alerts) are not real alternatives here, so the cost of that omission is low.

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?

"Use it when someone asks where a flight is, whether it is delayed, or when it lands" gives concrete triggering intents, which is more than most definitions do. There is no explicit when-not guidance (e.g. historical flights, multi-leg itineraries), but the day enum implicitly bounds usage.

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, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: results are cheapest first with live prices in USD, and if no single plan covers every country the tool returns one eSIM per country. It also implies a returned code that feeds into get_esim_plans. These are useful operational details that annotations alone would not convey.

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 front-loaded with the core purpose and then gives usage conditions and follow-up steps. The list of example hub cities is helpful but adds length; nevertheless, each sentence provides a distinct piece of information. It is appropriately sized for a search tool with a nuanced routing condition.

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, so the description must carry the return-value burden. It explains that results are plans on one QR code, cheapest first, priced in USD, with a fallback of one eSIM per country if no combined plan exists, and that a returned code is used with get_esim_plans. This is enough for an agent to invoke the tool and understand what comes back, though it does not describe the full response shape.

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 100%, so the individual parameters are already documented. The description adds semantic value by explaining that 'via' and 'to' must both be covered by a single plan, and that an optional second stop is supported. This clarifies how the parameters interact to produce a combined-coverage result, which is more than the schema provides.

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 and resource: finding Slashtel travel eSIM plans that cover both a transit hub country and a destination on one QR code. It distinguishes this from generic plan lookup by emphasizing combined layover-and-destination coverage, cheapest-first ordering, and live USD pricing. An agent can tell exactly what this tool does 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?

The description gives clear when-to-use guidance: trips with a connection through hubs such as Dubai, Doha, Istanbul, Singapore, and others, where data is needed during the layover and on arrival. It also explains the follow-up path with get_esim_plans and create_checkout_link, which helps an agent sequence calls. It stops short of explicitly saying when not to use this tool versus a single-destination search, so it is strong but not exhaustive.

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?

The annotations already cover read-only, idempotent and open-world behavior. The description adds context beyond them: the tool performs an operator-detection step against live data, and it describes the payload fields (what the recipient receives, validity, USD price) and the input-format precondition.

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?

It leads with the purpose ("Mobile recharge..."), pauses only to list the returned item types, and ends with the format requirement and an example. Every clause adds information, and no sentence is redundant.

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 one-parameter read tool with annotations but no output schema, it adequately describes both what goes in and what comes back. Minor gaps: it says nothing about behavior when operator detection fails or about whether prices are always in USD for non-US numbers.

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 one parameter is already documented, which sets the baseline at 3. The description earns a 4 by adding a concrete format example (+911234567890) and explaining why the country code matters: operator detection depends on it.

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 and resource: it detects the carrier for a phone number and returns live recharge/top-up options, broken down into airtime, data packs and plans. It implies the difference from get_esim_plans (mobile recharge versus eSIM), but never names that sibling explicitly.

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 text says what the tool does, so the use case is implied: get recharge options for a given number. It does not say when to choose this over get_esim_plans, check_phone_compatibility or check_esim_status, and it never states when not to use it, such as for landlines or numbers without a carrier.

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, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds non-obvious behavior beyond that: the catalog size (~200), that prices are 'live' rather than static, and that each row carries a plan count alongside the price. It stops short of mentioning pagination or result ordering, so it is not a full 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?

Three tightly packed sentences, front-loaded with what the tool returns before branching into usage and the alternative. Every sentence carries actionable information and 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?

With no output schema, the description carries the return-value burden and does so by listing the four fields returned. Combined with the destination count, the known-code bypass, and the read-only annotations, an agent has everything needed to call this correctly in one shot.

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 100% and the single `search` parameter is fully documented there, so the baseline is 3. The description's note that empty search lists everything is essentially a restatement of the schema text; it adds no new syntax, matching rules, or case-sensitivity guidance.

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 (list eSIM destinations sold by Slashtel), quantifies scope (~200 destinations), and enumerates the returned fields (code, name, lowest live price in USD, plan count). It also names a sibling (get_esim_plans), so an agent can distinguish the lookup tool from the plan-detail tool without opening either 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 explicit triggers (user names a place, a region like Europe or Asia, or is unsure what is covered) and an explicit exclusion plus alternative (skip this and call get_esim_plans directly when the ISO-2 code is already known). Both the when and the when-not are covered.

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