Caribbean Data API — Tropical Autonome

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

The description discloses that the tool is a paid service with a price of 0.500 USDC, which is a significant behavioral trait beyond the readOnlyHint annotation. It also clarifies it is an AI analysis (Claude) producing specific metrics. However, it does not detail payment flow or rate limits, but the cost disclosure adds important context.

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, efficient sentence that front-loads the core purpose, lists key outputs, and ends with the price. 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 tool with 9 parameters and no output schema, the description provides a good overview by listing expected outputs and cost. However, it omits details on how the analysis is returned (format, structure) and does not explicitly state the geographic scope (Caribbean/French overseas) though the tool name and EDF/crédit terms imply it. This is a minor gap but not critical.

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 covers 100% of parameters with descriptions, so baseline is 3. The description does not add further meaning to the parameters themselves, only listing output metrics like production kWh and TRI. It does not map parameters to outputs or explain how inputs affect the analysis.

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 states the tool performs a solar profitability analysis (Analyse rentabilité solaire), listing specific outputs: production kWh, EDF OA revenues over 20 years, TRI, and credit 244W. It distinguishes itself from sibling tools that are all 'get_' data retrieval tools by being the only analysis 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?

The description implies use for solar profitability analysis but does not explicitly state when to use it vs alternatives or mention any exclusions. It lacks explicit guidance like 'use this when you need a full financial analysis' or 'for raw data, use get_edf_oa_tarifs instead.' The context is implied but not made explicit.

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, so the read-only nature is known. The description adds the price and content type, which is useful, but it does not clarify the payment flow or what happens if payment_tx_hash is omitted, leaving some behavioral ambiguity.

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 extremely concise, consisting of two short sentences. Every word adds value: the first defines the content scope, and the second states the price. No filler or 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?

The tool is simple, with one optional parameter and read-only annotations, so the description is mostly adequate. However, there is no explicit statement about what the tool returns, and the payment logic is unclear; the description would benefit from a phrase like 'returns biodiversity data for Guadeloupe after payment.'

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 provides a full description for the single parameter (payment_tx_hash: 'Hash tx USDC Base'), so schema coverage is 100%. The description adds no additional meaning specific to the parameter beyond the given 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 resource (Guadeloupe biodiversity) and provides concrete details (10,600 species, ecosystems, protected areas), distinguishing it from sibling tools. However, it lacks an explicit verb like 'returns' or 'provides,' making the action implicit from the tool name.

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?

There is no guidance on when to use this tool versus alternatives. The mention of 'Prix : 0.050 USDC' hints at a payment requirement, but it does not explain prerequisites, context, or when to choose this over sibling tools.

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 readOnlyHint annotation is present, but the description adds only a price mention ('Prix: 0.050 USDC') without explaining the tool's behavior, such as what happens when the payment_tx_hash is provided or what data is returned. No additional transparency beyond the annotation.

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, but it is under-specified and promotional. The single sentence does not earn its place because it fails to explain the tool's function or structure, making it more like a tagline than a functional description.

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 tool with a payment parameter and no output schema, the description is grossly incomplete. It omits what the tool returns, how the payment hash is used, and whether any prerequisites exist. The agent cannot understand the tool's full 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?

The schema's description of payment_tx_hash covers 100% of the parameter. The description does not add any extra semantic value for the parameter, but the schema already provides adequate meaning, so the baseline 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 is a promotional phrase about a Caribbean agro-processing market, but it does not state an action or resource. It lacks a verb like 'get' or 'retrieve', making it vague and not distinguishable from sibling tools by functionality.

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 guidance is given on when to use this tool versus alternatives. It does not mention use cases, prerequisites, or comparable sibling tools, leaving the agent without the context needed to choose correctly.

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 annotation readOnlyHint=true already signals a safe read operation. The description adds some context (market data specifics) but fails to explain the role of payment_tx_hash in a read-only tool or whether any external calls are made. It does not contradict the annotation, but also does not meaningfully disclose behavior beyond it.

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 and mostly to the point, but it is structured as a series of fragments (e.g., 'Marché 2.1 Mds$. Prix : 0.050 USDC.'). It lacks a leading sentence that states the tool's purpose, making it feel disorganized despite its brevity.

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 and an unexplained optional parameter, the description is incomplete. It leaves the agent unsure what the response will contain or why a payment hash is needed. The specific figures (2.1 Mds$, 0.050 USDC) are ambiguous—whether they are constant outputs or examples is unclear.

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 has one optional parameter with a short description ('Hash tx USDC Base'). Since schema explanation coverage is 100%, the baseline is 3. The tool description does not elaborate on the parameter, so no additional value is 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 conveys that this tool is about the Caribbean vanilla market with specific details (prices, harvest, certifications, channels). However, it lacks an explicit verb like 'get' or 'retrieve', reading more as a fragment than a clear purpose statement. It does distinguish from sibling tools by naming vanilla specifically.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, scenarios, or exclusions. The description simply lists market details, leaving the agent to infer usage from the tool name.

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 readOnlyHint annotation, the description discloses a cost of 0.050 USDC, which is a behavioral trait. However, it does not explain how the cost is applied, whether payment is mandatory, or what the payment_tx_hash parameter is for, leaving the payment behavior ambiguous. Still, it adds some useful context beyond the annotation.

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 brief and every word carries information, making it concise. However, it is fragmented, using keyword-style phrases rather than a clear, structured sentence, which slightly reduces clarity.

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 appears to be a paid data service, but the description does not clarify what the output will be (e.g., a report, data table, or text), whether payment is required to access the data, or how the payment_tx_hash parameter is used. With no output schema and no further details, the description leaves significant gaps for a tool that may require payment.

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 fully describes payment_tx_hash as 'Hash tx USDC Base' (100% coverage), so the baseline is 3. The description mentions the price but does not explicitly link it to the parameter or add any additional meaning beyond what the schema already 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 clearly identifies the tool's focus: Caribbean vetiver luxury perfumery, with specific elements (price comparison between Haiti and India, olfactory profile, Guadeloupe potential). This distinguishes it from sibling tools like caribbean_get_caye_vanille (vanilla) and caribbean_get_biodiversite, and the 'get' verb in the tool name is reinforced by the concrete data points listed.

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?

There is no guidance on when to use this tool versus alternatives, no mention of prerequisites, and no exclusions. The price note ('Prix: 0.050 USDC') is not a usage guideline and does not explain the conditions for using the 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?

The readOnlyHint annotation already signals safety, but the description adds only domain context (standards, price) and no behavioral details such as what action it performs, what it returns, or how the payment_tx_hash parameter fits into a read-only operation. It does not contradict the annotation, but it does not meaningfully disclose behavior beyond it.

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 front-loaded with the key resource name. There is minor redundancy between 'prix marché USD/unité' and 'Prix : 0.100 USDC', but overall it wastes little space, though it may be too terse to be fully useful.

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 should explain what the tool returns, but it only lists topic labels and a price. It also leaves the payment_tx_hash parameter's role unexplained, creating a significant gap for a tool that combines read-only annotation with a payment-related input.

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% for the single parameter payment_tx_hash, so the schema already documents it. The description adds no parameter-level meaning, and notably does not explain why a payment hash is present in a supposedly read-only tool, but the baseline of 3 applies because the schema carries full parameter coverage.

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 resource (Caribbean biodiversity credits) and scope (TNFD, Plan Vivo, Verra, NatureMetrics, market price), which is clearer than the name alone. However, it lacks an explicit verb such as 'retrieves' or 'lists', and does not clearly distinguish itself from the sibling tool caribbean_get_biodiversite.

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 guidance is provided on when to use this tool versus alternatives. It does not name conditions, exclusions, or compare with related tools like caribbean_get_biodiversite, leaving the agent to infer usage from the resource label.

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 readOnlyHint annotation already signals a safe read operation. The description adds informational context by specifying the geographic focus, key entities (SMGEAG), investment scale, and the price of 0.050 USDC, which is relevant for invocation. However, it does not elaborate on return behavior, pagination, or other side effects beyond what the annotation already covers.

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 compact single sentence, front-loaded with the topic 'Eau et assainissement DOM,' and packs useful facts (loss rate, budget, timeframe, keywords) without unnecessary fluff. It is somewhat dense but appropriately sized for a data-retrieval tool.

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 has no output schema and only one optional parameter, the description partially compensates by listing likely content areas (crisis, tenders, desalination, chlordécone). However, it does not explicitly state the return format, structure, or how to interpret the output, leaving the agent to infer that it returns data about these topics.

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 the only parameter (payment_tx_hash) with a clear description to 100% coverage. The description adds the price point but does not explain payment mechanics or parameter usage beyond the schema. Thus, the schema carries the load, and the description offers minimal additional semantic value.

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 domain: water and sanitation in French overseas departments (DOM), specifically focusing on Guadeloupe's water crisis, SMGEAG, infrastructure budget, and related issues. It distinguishes itself from sibling tools by topic (e.g., solar, biodiversity, tourism). However, it lacks an explicit verb like 'retrieve' or 'get,' so it reads more as a content summary than a functional statement.

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 provides no guidance on when to use this tool versus alternatives such as caribbean_get_marches_publics or caribbean_get_financement_dom. It only implies by topic that it is for water/sanitation data, but there is no explicit context on suitable use cases or exclusions.

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?

Despite the readOnlyHint annotation, the description adds no behavioral context. It fails to disclose that the tool may return either payment instructions (when no payment_tx_hash is provided) or actual tariff data, nor does it explain response format or any dependence on payment state. The domain facts (20-year contracts, 0.020 USDC) are not behavioral.

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 extremely concise and front-loaded, using three short fragments to convey the core subject, scope, and key pricing details. Every sentence earns its place with no redundant wording.

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 and a payment-dependent behavior, the description is incomplete. It does not explain what the response contains in either case (payment instructions vs tariff rates), nor how the payment hash affects execution. A user would not know what to expect or how to proceed.

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 payment_tx_hash with a clear description (hash format and behavior when absent), achieving 100% schema coverage. The tool description adds nothing about the parameter beyond what the schema provides, so it stays at 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 states the tool provides EDF OA feed-in tariffs for solar energy in specific ZNI regions (971, 972, 974, 976), with contract length and price. This specific verb+resource+scope distinguishes it from sibling tools like caribbean_get_irradiation_dom or caribbean_get_raccordement.

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 no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or related tools. The only implied usage is 'when you need these tariffs,' but there is no explicit contextual instruction.

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?

While readOnlyHint already indicates a safe read operation, the description adds important behavioral context by disclosing the data source, species counts, protocol, and a price of 0.100 USDC, implying a paid transaction. This goes beyond the annotation and helps set expectations about cost and data provenance.

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, compact sentence packed with useful specifics: geographic area, institution, year range, species counts, protocol, and price. No filler or 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 simple data-retrieval tool with one optional parameter, the description provides good context about the data content and pricing. However, it lacks details on how to actually obtain the data (e.g., is payment_tx_hash required to trigger data delivery?) and does not mention return format or authentication, leaving some ambiguity for an agent.

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% for the single optional parameter payment_tx_hash, which already explains it is a USDC Base transaction hash. The description's mention of price (0.100 USDC) indirectly relates to the parameter but does not clarify whether the hash is required, optional, or how it is used.

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 providing marine eDNA data for Guadeloupe from MNHN 2021-2022, with specific details on species counts and protocol. While no explicit verb like 'retrieve' is used, the content strongly implies a data access tool and distinguishes it from sibling tools via the eDNA topic.

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 guidance is given on when to use this tool versus alternatives such as caribbean_get_biodiversite or other data access tools. The mention of price is transactional but does not help an agent decide between this and related tools.

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 declare readOnlyHint=true, so the read-only nature is covered. The description adds price information ('Prix : 0.050 USDC') and domain content, but it does not disclose the payment workflow, such as the role of payment_tx_hash or potential errors without payment.

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 extremely short and front-loaded with the main noun phrase, listing key programs without fluff. It loses a point for lacking an explicit verb, which would make the purpose clearer.

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 paid tool with no output schema, the description should explain the payment flow and what the agent will receive. It only lists content topics and price, leaving significant gaps in usage context and expected 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?

The schema already describes 'payment_tx_hash' as 'Hash tx USDC Base,' giving 100% coverage. The description adds meaning by connecting the parameter to the cost ('Prix : 0.050 USDC'), clarifying that the hash is likely for payment.

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 ('Aides financement ENR en DOM') and lists specific program names, distinguishing it from sibling tools about solar, water, or biodiversity. However, it lacks an explicit verb; the tool name 'caribbean_get_financement_dom' supplies the action.

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 provides no guidance on when to use this tool versus alternatives like caribbean_get_eau_dom or caribbean_get_raccordement. There is no mention of prerequisites, exclusions, or preferred use cases.

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 description discloses the price (0.100 USDC), which is relevant behavioral context not captured by the readOnlyHint annotation. However, it does not clarify whether payment is mandatory for full output, what happens without a valid hash, or any other operational behavior.

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 brief and informative: a short phrase listing the key facts (rates, form, cases) and the price. Every element has purpose, and it's well-structured for quick scanning.

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 has one parameter, no output schema, and read-only annotation. The description gives a snapshot of the content but omits what the user actually receives (e.g., a document, data fields) and the payment workflow. It's sufficient for a simple, narrowly-scoped tool but leaves gaps around expected 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?

The schema describes payment_tx_hash as 'Hash tx USDC Base.' The description adds the cost amount (0.100 USDC), tying the parameter to the payment requirement. This goes beyond the schema's minimal description, though it still doesn't explicitly connect the hash to the payment.

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: the 244 quater W DOM tax credit, with specific rates and form reference. However, it lacks an explicit action verb (e.g., 'returns' or 'provides'), so it reads more as a content summary than a functional description.

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 guidance is given on when to use this tool or how it differs from the many sibling caribbean_get_* tools. There is no mention of alternatives or exclusions, leaving the agent to infer usage solely from the name and topic.

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 readOnlyHint annotation already covers safety; the description adds the paid nature (0.050 USDC) and the specific data content, giving the agent a solid understanding of what to expect. It does not describe the output format, but the parameter schema handles payment instructions.

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?

One compact sentence packs geographic scope, price ranges, rent figures, and institutions without redundancy. The information is front-loaded and every element contributes to the tool's purpose.

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 absence of an output schema, the description sufficiently conveys the tool's content and cost, and the parameter schema explains the payment flow. It could be more explicit about the returned data format, but overall it is adequate for an agent to decide when and how to invoke it.

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 documents the single payment_tx_hash parameter with 100% coverage, including the meaning of its absence (payment instructions). The description adds no extra parameter semantics beyond the price, so the baseline of 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?

The description specifies the exact domain (agricultural land in French overseas departments) and enumerates concrete data topics (prices per zone, agrivoltaic rents, SAFER, FEADER, case studies). This clearly distinguishes it from sibling tools covering other domains like solar, biodiversity, or water.

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 provides clear context: this tool is for agricultural land data in Guadeloupe, Martinique, and La Réunion. While it does not explicitly name alternatives or exclusions, the topic specificity makes the intended use obvious among the sibling tools.

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 readOnlyHint annotation is consistent with the description. The description adds valuable behavioral context by stating the price (0.050 USDC) and implying a payment requirement, which is not covered by annotations. It does not contradict the annotation.

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 a colon, listing key content and price. It is efficient and front-loaded, though it uses abbreviations (AOC, HE) that could be expanded for clarity.

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 lack of an output schema and only one optional parameter, the description covers the main content areas and pricing. It does not describe return format, but for a read-only information tool with a simple schema, this is reasonably 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 input schema has 100% coverage, describing the payment_tx_hash parameter clearly. The description adds only indirect context (price) but does not elaborate on the parameter beyond what the schema already states, which is acceptable given the baseline of 3 for full schema coverage.

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 domain (import/export Caribbean customs flows, Dubai opportunities, logistics, certifications) and distinguishes it from siblings by its specific subject area. Though it lacks an explicit verb like 'get', the tool name contains 'get' and the content list makes its purpose evident.

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 guidance is provided on when to use this tool versus alternatives. It does not mention any exclusions or alternative tools, leaving the agent to infer usage solely from the domain name.

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 readOnlyHint annotation is consistent with the read-only nature. The description adds valuable context beyond the annotation by specifying data sources (NASA POWER + Solargis), the inclusion of a kWh/year formula, and the price (0.020 USDC). No contradiction.

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 concise sentences deliver the core purpose, scope, data sources, formula, and price. Front-loaded and free of 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?

The description covers dataset scope, regions, data sources, formula, and price. With no output schema, a bit more detail on the return format could help, but for a simple data retrieval tool with one optional parameter, it is adequately 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 schema fully describes the single optional parameter (payment_tx_hash) with 100% coverage, including the behavior if absent. The description does not add parameter semantics but does not need to since the schema is complete.

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 explicitly states the tool provides solar irradiation (GHI + PVOUT) for French overseas departments, lists the specific regions (Guadeloupe, Martinique, La Réunion, Mayotte), and mentions data sources. This clearly distinguishes it from sibling tools that cover other datasets.

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 provides clear context: this is the tool for solar irradiation data in DOM communes, with data sources and price. It does not explicitly name alternatives or exclusions, but the sibling tools are all distinct topics, so usage is effectively 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 readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds that it is 'Gratuit' (free) and a recommended starting point, which is useful context, but it does not describe the return format or pagination. Given the annotation coverage, the description provides minimal but acceptable transparency.

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 that front-loads the primary purpose and includes key usage context (free, recommended starting point). 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 simple read-only tool with no parameters and no output schema, the description covers the essential aspects: what it provides, the discovery URLs, and its role as a starting point. It could mention what the agent should do with the URLs, but the description is otherwise complete for a tool of this complexity.

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 schema is trivially complete. The description adds no parameter-specific information because none is needed. The baseline for 0 params is 4, and the description appropriately focuses on the tool's purpose rather than params.

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 states the tool provides an overview of the marketplace, listing available tools and discovery URLs (llms.txt, openapi.json, mcp). It is distinct from sibling tools by positioning itself as the recommended starting point, differentiating from more specific 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?

The description says 'point de départ recommandé' (recommended starting point), providing clear context for when to use this tool first. It does not name specific alternatives or exclusions, but the implied guidance is sufficient for a simple entry-point 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?

Annotations already declare readOnlyHint=true, but the description adds valuable behavioral context: real-time freshness ('Données fraîches à chaque appel') and a cost of 0.030 USDC. It does not contradict the annotation, and the price disclosure exceeds 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?

The description is compact and front-loaded with the primary purpose, then lists filters, freshness, and price in a somewhat run-on sentence. It is efficient, though the single-sentence structure could be broken up for better readability.

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 does not explain the response format beyond the existence of 4,400+ contracts. It also omits the payment flow (e.g., needing payment_tx_hash or receiving payment instructions) which is only in the parameter description. This leaves gaps for an agent about how results are returned and how payment works.

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 fully describes all 5 parameters (100% coverage). The description merely restates the filters (nature, année, pagination) already present in the schema, adding no additional semantic detail beyond what structured fields provide.

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 states it fetches public contracts ('Marchés publics') for Guadeloupe (971) in real time from the official DECP database. This specific verb+resource+scope distinguishes it from the sibling 'caribbean_get_marches_publics_dom' which likely covers all French overseas territories.

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 use when Guadeloupe public contracts are needed, but does not explicitly contrast with the DOM-wide sibling. It lacks explicit when-to-use vs. alternative guidance, though the geographic scope is a clear contextual signal.

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 include readOnlyHint=true, confirming a safe read operation. The description adds real-time status, official DECP source, and pricing (0.025 USDC), which are beyond annotations. However, it does not disclose pagination behavior, rate limits, or payment flow details beyond the price, leaving some transparency gaps.

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, tightly packed sentence conveying scope, data volume, specific departments, official status, filters, and price. Every clause adds value, with no redundancy or filler, and key information is front-loaded.

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 retrieval tool with strong annotations (readOnlyHint=true) and full schema coverage, the description adequately covers purpose, scope, filters, and pricing. The absence of an output schema is mitigated by the clear use case, though the payment mechanism (via payment_tx_hash) is only hinted at by the price, leaving minor completeness gaps.

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 baseline is 3. The description mentions filters (département, nature, année) but only restates schema parameter names without adding deeper semantic meaning or relationships. It does not clarify parameter interactions or value formats beyond what the schema already 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 clearly identifies the resource (public contracts) and scope (all DOM, specific departments enumerated) but lacks an explicit verb like 'list' or 'retrieve'. The tool name includes 'get', so overall purpose is clear and distinguished from the sibling 'caribbean_get_marches_publics' via '_dom' and 'tous DOM'.

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 provides usage context (real-time, all DOM, filters) and notes it covers all DOM, implying use for broader scope. However, it does not explicitly state when to use this over the sibling 'caribbean_get_marches_publics' or any exclusions, so guidance is implied rather than direct.

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 and openWorldHint, so the bar is lower. The description adds the commission-inclusive pricing detail and third-party data source context, but does not disclose potential rate limits, auth requirements, or return behavior. This is modest added value beyond 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 two sentences, front-loaded with the core action, and every clause earns its place. It is succinct without sacrificing essential usage guidance.

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 generic getter with well-documented schema and annotations, the description covers the main usage prerequisite (list first) and a key business rule (commission). It does not describe return shape, but no output schema exists and the tool's purpose is fairly simple. Minor omissions like optional payment_tx_hash context are acceptable.

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 fully documents all three parameters with examples. The description reinforces the concept of 'slugs' but adds no new parameter-level meaning beyond what the schema already 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 clearly states the tool accesses data from a third-party marketplace provider, using a specific verb and resource. It differentiates itself from siblings by being a generic marketplace getter, though the exact nature of 'marketplace' isn't elaborated. The mention of commission adds specificity.

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 instructs to use caribbean_list_marketplace first to discover available slugs, establishing a clear prerequisite. This is strong usage guidance that also implicitly distinguishes when to use this tool versus the listing 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?

The readOnlyHint annotation already declares safe read behavior, and the description does not contradict it. The description adds the cost ('Prix : 0.050 USDC') which indicates a payment requirement, but it does not explain the payment flow or what happens when payment_tx_hash is absent. This is partial behavioral context beyond the annotation.

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 dense sentence with many statistics and prices. It is not excessively long, but the structure is a run-on list that mixes different types of information (tonnage, prices, regulation, export, cost) without clear organization. It could be more concise by focusing on the tool's function and usage.

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?

No output schema is present, so the description should clarify what the tool returns. It gives sample data points (e.g., langouste prices) but not a clear description of the response structure. It also does not explain the payment behavior (e.g., that providing a hash unlocks data, or that omitting it returns payment instructions), which is essential for using this paid 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?

The schema description for payment_tx_hash is complete (100% coverage), describing it as a transaction hash and noting 'Absent = instructions paiement'. The tool description mentions the price but adds no further semantic meaning to the parameter itself, so the baseline of 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 clearly indicates the tool is about Caribbean artisanal fishing, including specific statistics and prices, and the name reinforces this with 'get'. It distinguishes itself from sibling tools by its specific subject matter, but it lacks an explicit verb like 'retrieve' or 'get' in the description text itself.

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?

There is no guidance on when to use this tool versus alternatives. The description does not mention preferred use cases, prerequisites, or any exclusionary conditions. The only context is the domain itself, which is implicit from the name and content.

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 description discloses a price ('Prix : 0.050 USDC'), which is a meaningful behavioral trait beyond the readOnlyHint annotation. It also implies a payment requirement via the transaction hash parameter, adding valuable context that this is a paid data access tool. However, it does not detail the payment workflow or response behavior when payment is absent.

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 efficiently lists key data points and the price. It is front-loaded with the subject and contains no filler. But it is more of a data catalog summary than a clear functional description, slightly reducing structure value.

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 tool with one optional parameter and no output schema, the description gives a decent overview of the data content and cost. However, it does not explicitly state what the tool does or how the payment flow works, relying on the schema's param description. This is adequate but has gaps.

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 the parameter fully (hash format and 'Absent = instructions paiement'), and schema coverage is 100%. The description adds only the price, which is related but not extra parameter syntax or semantics. Baseline of 3 applies because the schema carries the parameter 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?

The description is a noun phrase ('Intelligence économique Guadeloupe') followed by a content list, but it does not state the tool's action. There is no verb like 'get' or 'retrieve'; the only verb is in the tool name, not the description. This makes the tool's purpose ambiguous beyond what the name implies.

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 a use case through its content (economic intelligence on Guadeloupe's SMEs), but it gives no explicit guidance on when to use this tool versus alternatives. Sibling tools cover different Caribbean topics, yet the description does not contrast with them or mention conditions.

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 description is not required to restate safety. It adds the fact that the tool is 'Gratuit' (free) and lists the types of information returned, which provides some additional context. However, it does not disclose potential limitations, rate limits, or data freshness.

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, front-loaded sentence that directly states the tool's purpose and key outputs. Every word contributes meaning, 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?

Given the simplicity of the tool (one parameter, no output schema), the description adequately covers what the tool returns. It lists the main fields but could be slightly clearer about what a 'provider' refers to in this context. Overall, it is sufficient for a basic read-only 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?

The schema provides 100% coverage for the single parameter provider_slug, including an example. The tool description adds no additional parameter semantics, so the baseline score of 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?

The description clearly states the tool's purpose: returning a provider's full card including description, endpoints, prices, and verification status. The verb 'Retourne' is specific, and the resource is identified as a provider. It distinguishes itself from sibling tools by focusing on provider metadata rather than specific data topics.

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 when to use the tool (to get provider details) but does not explicitly state when not to use it or mention alternatives. There is no direct comparison to sibling tools, though the context suggests this is for provider information. Clear but not comprehensive.

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 description adds the price (0.020 USDC) and content focus beyond the readOnlyHint annotation. However, it does not explain whether payment is required upfront, how the payment_tx_hash is used, or what happens if the hash is missing/invalid.

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 conveys the core purpose and price with no filler. It is front-loaded and efficient.

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 data retrieval tool, the description is adequate but leaves gaps: it does not specify the return format (text, structured data), whether payment is mandatory, or the workflow for using the payment hash. These omissions could confuse an agent deciding how to invoke the 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?

The schema already describes the only parameter (payment_tx_hash) as a USDC Base transaction hash, so schema coverage is 100%. The description mentions price but does not add additional meaning to the parameter itself, such as format or necessity.

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 states the tool provides a solar network connection procedure in Guadeloupe with 8 EDF SEI steps and real-field delays. This distinguishes it from sibling tools which cover other Caribbean topics like biodiversity or market data.

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 guidance is given on when to use this tool versus alternatives. The price is mentioned but there is no context about preferred use cases or exclusions compared to sibling tools.

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 readOnlyHint annotation covers the read-only nature. The description adds a price ('Prix : 0.050 USDC') and hints at payment requirements, but the schema already details the parameter behavior (absent payment returns instructions). There is no contradiction, but limited behavior is disclosed beyond the annotation.

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 concise and front-loaded with the topic, covering content and price in two short sentences. It is not excessively long, though it could be more structured as tool instructions.

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?

It provides a rich overview of the data content (visitor stats, sustainable labels, market flows, etc.) but does not explicitly state what the output format is, and the payment flow is only partially covered via the schema. The description is adequate but relies on the name and schema to convey full functionality.

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 fully describes the single parameter (payment_tx_hash) with its payment-related behavior, so the description need not add more. The description does not mention the parameter at all, which is acceptable given 100% schema coverage.

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 is a descriptive summary rather than a clear statement of function; it lacks an explicit verb indicating that it retrieves tourism data. However, the name and detail (e.g., '870 000 visiteurs 2024') make the subject clear, distinguishing it from sibling tools on other topics.

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 provides no guidance on when to use this tool versus alternatives. It does not mention any conditions, exclusions, or related tools; the topic is implied by the name but not explicitly stated as a recommendation.

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 safe read nature is known. The description adds value by noting 'Gratuit' (free) and that only active providers ('actifs') are returned, plus the included fields (endpoints and prices), giving context beyond the 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 a single sentence plus a one-word sentence, front-loaded with the verb and object. Every word earns its place; 'Gratuit' adds a distinct behavioral detail without bloat.

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 list tool with no output schema, the description sufficiently covers purpose, scope (all active providers), and content (endpoints and prices). It could add a note on result size or pagination, but that is not critical given the simple nature and existing sibling tools.

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 has zero parameters, so the baseline is 4. The description's mention of 'tous les fournisseurs actifs' confirms the tool takes no filters, matching the empty schema. There are no parameters to document.

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 states the tool lists all active Caribbean marketplace providers with their endpoints and prices. It uses a specific verb ('Liste') and resource ('fournisseurs actifs de la marketplace caribéenne'), and the inclusion of endpoints and prices distinguishes it from siblings like caribbean_get_provider.

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 context is implied: this is for listing all active providers, versus getting a single provider or raw marketplace data. However, no explicit alternatives or exclusion criteria are mentioned, so the agent must infer when to use it versus the sibling get_* tools.

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