eurocollis

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

No annotations are present, so the description carries the behavioral burden. It usefully discloses that rates are live and based on MAD, and that only EuroCollis-supported currencies are accepted. However, it does not mention whether the operation is read-only, what happens on invalid currency codes, or how rates/rounding are handled.

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 a single sentence with no filler. It front-loads the action and includes the most relevant constraint (supported currencies, live MAD-based rates) without repeating schema 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 simple three-parameter conversion tool, the description is minimally viable: an agent knows to provide an amount and two supported currencies. However, with no output schema and no parameter-level documentation, it lacks detail on return format, currency code conventions, amount restrictions, and error behavior.

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 0% and no enums exist. The description only generally references 'amount' and 'currencies', adding the fact that currencies must be EuroCollis-supported but failing to explain amount constraints, currency code format, or the roles of from_currency and to_currency in any detail. The property names are self-explanatory, but the description does not compensate for the schema gap.

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 ('Convert') and names a clear resource: an amount between EuroCollis-supported currencies. It also adds the distinguishing detail that rates are live and MAD-based. No sibling tool performs currency conversion, so this definition makes selection unambiguous.

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 implies the tool is for converting amounts between supported currencies, but it does not state when to prefer it over alternatives or mention any related tools such as get_quote or estimate_customs. There is no explicit context or exclusion 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?

With no annotations, the description carries the behavioral burden. It discloses that results are indicative, not authoritative, and that the response contains a disclaimer that must be rendered verbatim. This is meaningful behavioral context beyond the bare operation.

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 entire description is one short sentence with the key qualification front-loaded. No wasted words; the disclaimer requirement 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?

The description is adequate for a simple estimation call and covers the critical output caveat, but without an output schema or annotations it leaves parameter meaning and response shape partially implicit. The optional category in particular is left unexplained.

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 33% (destination_country has an ISO description). The description does not explain declared_value_eur or the optional category, nor how they affect the estimate, so it fails to compensate for the sparse 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?

The description names the exact resource (customs duty and VAT) and the action (estimate), and flags the indicative nature. This is distinct from the sibling tools, which concern shipping quotes, routes, and tracking.

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 purpose implies when to use the tool, and the 'NOT authoritative' warning sets expectations, but there is no explicit when-to-use vs alternative guidance or exclusion. It tells the agent how to handle the result rather than when to select this tool.

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?

With no annotations, the description carries the behavioral burden. It discloses that this is a read-only city lookup limited to one country and that output names are exact accepted values for get_quote. It does not detail invalid-country behavior or return structure, but the essential behavior is clear.

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, both necessary. The first states what the tool returns; the second explains how to apply the output. No redundancy or 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?

For a simple one-parameter read-only tool, the description covers the tool's purpose, scope, and downstream usage. It does not specify the exact JSON return shape, but no output schema exists and the description implies the returned values are usable as city strings, which is sufficient for invocation.

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 parameter country is already fully documented with its ISO-3166 alpha-2 format and examples. The description adds only the light context that cities are for one country, which does not significantly improve on 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?

The description clearly identifies the tool as returning supported pickup/delivery cities for a country, which is a specific resource and scope. It stands apart from siblings like get_routes or get_quote, and it explicitly ties the returned names to their use in get_quote.

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 practical usage context: fetch these city names and use them as origin_city/destination_city in get_quote. It does not explicitly state when not to use the tool or compare it with alternatives, but the intended workflow is obvious.

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?

No annotations are present, so the description must carry behavioral disclosure. 'Public' and 'No PII' indicate a read-safe operation and privacy boundary, but it doesn't cover not-found behavior, auth requirements, or response shape. Satisfactory but minimal.

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 contain the entire value: what is returned, the identifier criteria, and a privacy note. 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?

For a single-parameter lookup with no output schema, the description adequately explains the purpose and input. It could be more explicit about the returned profile fields, but the low complexity keeps this from being a major gap.

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% (the 'courier' parameter is described as 'Storefront slug or courier UUID'), and the tool description essentially repeats that. No additional format or validation details are added.

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 ('get') and resource ('public profile for one courier'), and specifies the two identifier types. 'One courier' distinguishes it from list/search siblings like search_couriers.

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?

Clear context: use when you have a storefront slug or courier ID and need the public profile. No exclusions or references to alternatives, so it isn't 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?

With no annotations, the description carries the burden of behavioral disclosure. It describes the scope of the returned information but does not explicitly state the operation ('returns', 'provides') or any constraints such as data being static or auth requirements. For a zero-parameter info endpoint this is a minor gap, but the description still adds no behavior beyond content topics.

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 a single sentence that packs all key topics without redundancy. The phrasing is slightly awkward ('What EuroCollis is, the corridors it operates...') but it is concise, front-loaded, and every listed item 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?

For a no-parameter, no-output-schema information tool, the description gives an agent enough context to decide whether to call it: it will provide an overview of EuroCollis plus corridors, currency, deposit model, and booking completion location. A small note that this is static reference information would make it more complete, but the essentials are present.

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?

The tool has zero parameters, so the input schema places no burden on the description. The description appropriately focuses on what the tool returns rather than input semantics, which is the correct trade-off for a parameterless endpoint.

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 clearly identifies the resource (EuroCollis) and the specific information provided: definition, corridors, currency, deposit model, and where bookings are completed. It stops short of a strong action verb like 'returns' or 'retrieves', and it does not explicitly differentiate from sibling tools, but the content scope is unambiguous.

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?

No explicit when-to-use or when-not-to-use guidance is given, and no alternative tools are mentioned. However, the usage is implied: an agent needing facts about EuroCollis itself—its corridors, currency, deposit model, or booking location—can infer this is the right tool. The lack of explicit routing to a sibling leaves the 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?

With no annotations, the description carries the behavioral burden. It discloses that the tool provides prohibited-item data and that it should be shown before booking, but it does not mention return structure, read-only nature, or potential error/empty-list behavior. This is adequate but not rich.

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 a single sentence with two concise clauses. It front-loads the core content (prohibited items) and then adds a direct usage instruction. Every word earns its place, with no redundancy.

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 zero-parameter tool with no output schema, the description covers the key aspects: domain (EuroCollis and Morocco/EU customs), content (prohibited items), and application context (surface before booking). It does not specify the output format, but the simple nature of the lookup makes this a minor gap.

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?

The tool has zero parameters, and the baseline for 0-parameter tools is 4. The description correctly adds no parameter details because none are needed; the schema already confirms an empty parameter set.

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 clearly identifies the tool's subject—prohibited items for EuroCollis and Morocco/EU customs—and conveys a retrieval action through the phrase 'Items ... prohibit'. It differentiates from siblings by being specifically scoped to prohibited-items data, though it does not use an explicit verb like 'retrieves' or 'lists'.

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 instruction 'Always surface before a booking recommendation' explicitly states when this tool should be used, providing clear context for an agent. It does not mention alternatives or exclusions, but the timing guidance is actionable and sufficient for this tool.

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?

With no annotations, the description carries the full transparency burden. It discloses that the tool is authoritative and uses the same pricing engine as the website, and it cautions against self-computation. However, it does not state whether the operation is read-only, what happens on invalid input, or any permission/rate considerations.

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 sentences, front-loaded with the tool's purpose, followed by input guidance and a non-recomputation directive. Every sentence earns its place with no redundancy or 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?

The description is adequate for identifying the tool and its two input modes, but it doesn't disclose output structure, and no output schema exists. It also leaves ambiguity about whether weight_kg and items[] are mutually exclusive, and it does not clarify response behavior for invalid or incomplete required parameters.

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 high at 75%, but the description adds meaningful semantic grouping: weight_kg is for boxes/suitcases while items[] is for catalogue goods. This clarifies the intended selection between two parameter families, which is not explicit in the individual schema 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 action: returns an authoritative price quote for Morocco ↔ Europe shipments from the website's own pricing engine. The resource and scope are clear, and the authoritative framing separates it from generic estimation tools, though it doesn't explicitly contrast with siblings like estimate_customs.

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?

Provides how-to guidance for inputs (weight_kg vs items[]) and a strong directive to never recompute prices, but gives no when-to-use guidance versus alternatives. Sibling tools such as estimate_customs or get_services are not mentioned, so an agent receives no routing or exclusion information.

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?

With no annotations, the description carries the full disclosure burden, and it does convey the key behavior: the tool returns all supported corridors and can optionally include live trip volume for a scoped corridor. However, it does not explain what 'live trip volume' means, whether the data is read-only, or any rate/recency caveats.

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 very short and mostly front-loaded, with the resource type stated first. It is efficient, though the first sentence is a fragment and the scoping behavior could be phrased more precisely, which keeps it from being perfect.

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?

This is a low-complexity listing tool with optional parameters and no output schema, and the description gives a reasonable high-level picture. It is incomplete on what fields the route objects contain, what 'live trip volume' looks like, and how country parameters map onto corridor selection.

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?

The input schema already documents both parameters with 'ISO-3166 alpha-2', so schema coverage is 100%. The description adds only the idea of scoping to a corridor, but it does not clarify how both parameters must be combined for 'one corridor', so it provides no meaningful semantic improvement beyond the 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 clearly identifies the resource as supported Morocco–Europe corridors and signals that the tool can optionally narrow to one corridor for live trip volume. It does not explicitly contrast itself with sibling tools like get_services or get_courier, so it stops short of a 5.

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 shows when optional filtering might apply ('Optionally scope to one corridor for live trip volume') but gives no guidance on when to choose this tool over the many sibling tools. There are no alternative tool references or exclusion conditions, leaving the agent to infer routing from the name 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?

No annotations are provided, so the description carries the full burden. It discloses the return concept ('catalogue with pricing units') and its relationship to get_quote, but does not explicitly state that this is a safe read-only operation or describe any other behavioral details.

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?

A single, tightly worded sentence conveys both the tool's purpose and its downstream usage. It is front-loaded and contains no filler or unnecessary repetition.

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 zero-parameter tool with no output schema, the description is largely complete: it names the resource, mentions pricing units, and tells the agent how to use the returned item_id values. It could be more explicit about the exact shape of the returned catalogue, but this is a minor gap given the tool's simplicity.

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?

The tool has zero parameters and 100% schema coverage, so the schema leaves nothing ambiguous. The description adds useful context about item_id output values being used in get_quote, which is sufficient for a parameterless tool.

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 identifies the tool as a 'Shippable item catalogue with pricing units', making its resource clear. It also differentiates it from get_quote by explaining that item_id values from this catalogue are consumed by get_quote, though it lacks an explicit verb like 'list' or 'retrieve'.

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 second clause gives clear usage context: the output item_id values are meant to be passed to get_quote. This implies when an agent needs the catalogue before quoting, but it does not explicitly mention alternatives or when not to use this tool.

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?

With no annotations, the description carries the behavioral disclosure burden. It usefully discloses that only published storefronts are returned, that output includes canonical URL and corridor pages, and that omitting the slug switches to list mode. It does not cover pagination, errors, or authentication, but the core behavior is transparent.

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 two compact sentences with no filler: the first defines what is returned, the second explains the key usage rule. Every sentence 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?

For a simple optional-parameter get/list tool, the description names the main return fields and the listing mode, but with no output schema or annotations it leaves gaps around the exact listing response shape, limit handling, and pagination. It is adequate but not fully complete.

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?

The slug parameter has no schema description, so 'Omit slug to list storefronts' provides essential semantic value by explaining that the parameter toggles between single-get and list behavior. The limit parameter is only minimally described in the schema, and the description reinforces its listing context but does not add defaults or bounds.

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 identifies the specific resource—'published courier storefront'—and its key output fields (canonical URL and corridor pages), and the name 'get_storefront' supplies the verb. It is distinguishable from sibling 'get_courier', though it does not explicitly name that sibling.

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 instruction 'Omit slug to list storefronts' gives a clear conditional usage rule. However, there is no explicit guidance on when to prefer this tool over siblings like get_courier or search_couriers, so the usage context is only partially stated.

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?

With no annotations, the description carries the full burden, and it does disclose the main behavioral filters: only live, verified couriers with upcoming departures are returned, while demos, unverified accounts, and past departures are excluded. It does not mention limit behavior or empty-result handling, but the disclosed filter set is meaningfully useful.

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 front-load the core resource and add a single high-value exclusion sentence. There is no redundant prose or repetition of schema 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?

The tool is simple and the description covers its main filtering behavior, but without an output schema or annotations it leaves ambiguity around whether origin/destination are expected together despite being listed as optional. It also never states a default or cap for limit; more guidance would make it fully self-contained.

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?

The schema already describes from_date, origin_country, and destination_country (75% coverage), so the description does not need to repeat them. It adds no extra meaning about how these parameters form the corridor or what limit controls, leaving that to 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?

The description identifies a concrete resource and scope: live, verified couriers with upcoming trips on a corridor. The exclusion of demo accounts, unverified couriers, and past departures sharpens the definition and distinguishes it from sibling tools like get_courier, which targets one courier.

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 exclusion criteria imply this tool is for finding real, bookable courier options for a corridor, but no sibling tool is named and there is no explicit when-to-use/when-not-to-use guidance. An agent must infer that get_courier or get_routes would be used for different tasks.

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?

With no annotations provided, the description carries the full behavioral burden. It discloses that the status is public, that both inputs are intentionally required to prevent enumeration, and that no PII is returned. These are meaningful behavioral traits, though it does not mention rate limits, error behavior, or the exact status data returned.

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 a single concise sentence with every clause earning its place: the main purpose is front-loaded, and the input requirement, rationale, and PII guarantee follow without redundancy or 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?

For a two-parameter lookup tool, the description gives enough to understand the core call and safety model. Still, since there is no output schema and no annotation coverage, the description leaves details about the response shape, status values, and possible failures unstated, creating a moderate completeness gap.

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?

The schema covers 'reference' with an example but leaves 'delivery_city' undocumented, so schema coverage is only 50%. The description adds the important semantic that both parameters are mandatory and that requiring the city is an anti-enumeration measure, but it does not clarify the expected format or semantics of delivery_city beyond its self-explanatory name.

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 'Public shipment status,' which is a specific verb-plus-resource statement that immediately identifies what the tool does. It also names the two required inputs and the security constraint, making it easy to distinguish from the currency, customs, and courier siblings.

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 implies the tool is for checking shipment status and stresses that both reference and delivery city are required ('anti-enumeration'), which gives important usage context. However, it does not explicitly state when to prefer this tool over alternatives or exclude cases where a sibling tool should be used.

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