fr-legal-kit

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

No annotations are provided, so the description carries the burden. It mentions 'Paid $0.01 USDC Base x402' and 'Own L441-9 sequence', which hint at side effects and state management, but it is not clear whether these are outputs, inputs, or actions. No clear disclosure of destructive or read-only 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 extremely brief but poorly structured. It reads as a stream of keywords without clear separation of purpose, parameters, or effects. This hurts clarity despite the short length.

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 insufficient for an agent to understand what the tool does, how to invoke it, or what to expect. There is no output schema and the description is too vague to serve as a complete guide. The tool appears to require domain-specific knowledge to interpret.

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 no defined parameters (coverage is 100% vacuous), so the baseline is 3. The description adds some terms like 'next AC- number' and '30% default or explicit %', but it is not clear how these map to actual parameters or usage, so the description provides marginal 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 mentions 'French down-payment (acompte) invoice' but does not clearly state the action (e.g., create, generate) or how it differs from sibling tools like arrhes or escompte. The rest of the text is cryptic and does not clarify the tool's purpose.

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 compared to alternatives. The description does not mention any conditions or contexts that would indicate this tool is appropriate.

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, and the description does not disclose whether the tool is read-only or has side effects. The unusual 'Paid $0.01 USDC Base x402' hint suggests a cost but is not clearly explained.

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 well-structured, providing essential information in one short sentence without unnecessary 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 simple data-retrieval tool with no parameters and no output schema, the description covers the core purpose and scope adequately. The cost hint could be clearer but does not detract significantly.

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 there is nothing to describe. The description is sufficient without parameter explanations.

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 that the tool provides Alsace-Moselle extra public holidays and a combined 2026–2027 calendar, distinguishing it from the general 'holidays' sibling tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Mentions that it is 'In addition to L.3133-1 metropolitan days' which implies it fills a specific gap, but does not explicitly state when to use it versus alternatives or when not to use it.

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 must carry behavioral detail; it mentions output style and example output but omits expected input format and includes a confusing payment-related fragment that is not explained.

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 but not concise because the final sentence 'Paid $0.01 USDC Base x402' is irrelevant and distracts from the tool's actual 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?

It provides an example and style rule, but lacks clarity about expected input, output format beyond the example, and the meaning of the stray payment reference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters in the schema, so there is little to describe; the baseline applies and no parameter confusion is introduced beyond the odd unrelated phrase.

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 produces French amount words for invoices and gives an example, but it includes irrelevant text about 'Paid $0.01 USDC Base x402' that slightly muddies the core purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It says 'for invoices' and 'Not a statutory mention,' but it does not explain when to use this tool versus alternatives or provide practical guidance on when it is appropriate.

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 of disclosure. It covers the essential behaviors: pure format validation, no external label lookup, and critically the $0.01 USDC Base x402 payment cost — a material side effect an agent must know before calling. It does not mention error behavior on invalid input, but for a simple check tool this is adequate.

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 front-loaded sentence with zero filler. Every clause earns its place: the purpose, the format spec, the no-lookup limitation, and the payment disclosure. Model-efficient and complete.

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 format-check tool with no output schema, the description covers purpose, input format, scope limitations, and cost. The main gap is the unspecified input-passing mechanism given the permissive additionalProperties schema, and the absence of any hint about the return value (boolean vs. error). Minor 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?

There are 0 defined parameters, giving a baseline of 4. However, the schema sets additionalProperties: true, meaning arbitrary key-value pairs are accepted, and the description never explains what key or format to use to pass the code to validate. The format pattern (4 digits + letter) partially clarifies the expected value, but the input mechanism remains ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'format check' of 'French APE/NAF rev.2' with an exact format pattern (4 digits + 1 letter, e.g. 62.01Z). This clearly distinguishes it from siblings like check_siret and check_iban, which validate different code types. The 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?

The 'No INSEE lookup of the label' clause implies the tool is for structural validation only, not for retrieving semantic label data — which is useful scoping. However, no explicit when-to-use guidance or named alternative is provided, so routing relies on inference from the sibling list rather than direct 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?

With no annotations, the description must carry the transparency burden. It explains the legal meaning of arrhes (buyer forfeits, seller returns double) but says nothing about the tool's side effects, mutability, or whether it is read-only. The payment example hints at a transaction but does not clarify state changes.

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, not overly long, but it packs in legal references, distinctions, and a payment example. It is concise but sacrifices clarity for 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?

Given the open schema and lack of annotations, the description is the only context. It explains the concept and a required parameter, but it fails to specify what the tool returns, how it executes, or its exact role among the many sibling tools. The example payment is not contextualized sufficiently.

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 description explicitly mentions 'Requires amount_eur', which is a parameter requirement, but the schema itself only has additionalProperties: true with no defined properties. The 'Paid $0.01 USDC Base x402' part is unclear—it could be an example value or a different parameter. Other potential parameters are not explained.

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 defines the legal concept of arrhes and distinguishes it from acompte, but it does not state the tool's actual action (e.g., create, calculate, process). It is cryptic with 'Paid $0.01 USDC Base x402' suggesting a payment example, yet the core function remains ambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It mentions 'distinct from acompte' which provides a contrast, but offers no explicit guidance on when to use this tool versus the acompte tool. The requirement for amount_eur is a prerequisite, not usage direction.

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 disclose side effects. It fails to do so; the cryptic 'Paid $0.01 USDC Base x402' suggests a payment or on-chain action but is not explained. No side effects on invoices or other resources are mentioned.

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 run-on sentence that mixes multiple disjointed concepts. It lacks clear structure and logical flow, making it difficult to parse. Concision is absent because each fragment adds confusion rather than 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 simple schema (no params, no output), the description is the sole source of context. It is incomplete and misleading, leaving the agent without essential information about the tool's function, input requirements, or 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 has zero parameters, so parameter coverage is complete by default. The description does not add any parameter semantics, but since there are none to clarify, 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 is a jumble of unrelated phrases ('self-billing stamp', 'CGI 289', 'word Autofacturation', 'Optional seller name', 'Prior agreement is the buyer's problem', 'Paid $0.01 USDC Base x402'). It does not clearly state what the tool does, making it impossible for an agent to understand its purpose.

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. The mention of 'French self-billing stamp' hints at a use case, but the rest of the description confuses rather than clarifies, offering no concrete conditions or examples.

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 must carry the full burden of disclosing side effects. It mentions 'Paid $0.01 USDC Base x402' which suggests a payment or fee but does not clarify whether this tool triggers a payment, returns a mention, or performs an action. The description is otherwise purely informational and does not state whether it mutates data or has side effects.

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 but packs multiple pieces of information: legal basis, invoice treatment, and a payment detail. It is concise and to the point, though the 'Paid $0.01 USDC Base x402' phrase is somewhat out of place and reduces clarity. Overall, it is well-structured for a simple mention generator.

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 no parameters and no output schema, the description provides sufficient context: it defines the reverse-charge mention, relevant legal articles, and how the invoice is presented. The 'Paid' line is ambiguous but does not prevent understanding of the core function. It could be improved by explicitly stating that the tool returns a text mention, but it is largely 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 is empty (type object with additionalProperties true) and the description mentions no parameters. With zero parameters, the baseline is 4, and no additional parameter explanation is needed. The description provides sufficient context about the tool's purpose without requiring parameters.

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 that the tool provides the French reverse-charge VAT mention (autoliquidation) with specific legal references (CGI 283, 283-2 nonies, import). It also explains the invoice shows HT and VAT is due by the customer, making the purpose unambiguous. The name and description align perfectly.

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 lists the applicable contexts (intra-EU, construction, import) and indicates the invoice shows HT with VAT due by the customer. It does not explicitly name alternative tools from the sibling list, but the specific legal references and context clues make it clear when to use this mention. Slightly more explicit guidance could push it to 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?

The description discloses a notable side effect: 'Paid $0.01 USDC Base x402' indicates a cost for using the tool. It also mentions 'Format only' suggesting limited behavior (no validation or extraction). No annotations exist, so the description carries the burden and does disclose some behavioral traits.

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 but includes extraneous and confusing information: 'Paid $0.01 USDC Base x402' appears irrelevant to the tool's purpose and disrupts the flow. Additionally, 'Format only' is ambiguous and adds noise without clarity. The structure is not clean or focused.

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 provides some context (legal reference, B2C condition) but omits essential details such as the expected output structure, return format, or how the tool integrates with the invoice data. It is incomplete for an agent to fully understand the tool's behavior and invocation requirements.

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?

With zero parameters in the schema, the baseline is 4. The description adds some semantic meaning by listing the expected fields (client name, optional SIRET/SIREN, city) that likely constitute the input structure, though it does not formally define how these are passed. This partially compensates for the open 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 states the tool's purpose: French invoice buyer identification, mentioning key fields (client name, optional SIRET/SIREN, city) and a relevant legal reference (L441-9). It is specific enough to differentiate from siblings that handle other aspects like SIREN extraction or legal mentions.

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 a usage condition ('B2C may omit SIRET') which guides when the tool is applicable, but does not explicitly compare to alternative sibling tools or state when NOT to use it. The phrase 'Format only' is vague and does not clarify the intended invocation context.

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

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

The description discloses that the tool is 'format only' and not a Kbis, indicating it returns a textual mention without generating a legal document. Since there are no annotations (e.g., readOnlyHint), this text carries the transparency burden. It does not explicitly state whether it has side effects or requires payment, though the 'Paid $0.01' note hints at a possible fee.

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 relatively concise but includes the extraneous phrase 'Paid $0.01 USDC Base x402,' which appears unrelated to the tool's function and may confuse the reader. The core information is clear, but this noise detracts from the overall structure.

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 (no parameters, no output schema), the description provides sufficient context: it identifies the target legal forms, gives an example mention, and clarifies boundaries (not a Kbis, not for EI/micro). The payment note adds ambiguity, but the essential information for correct usage is 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 schema has zero parameters (100% coverage by default). The description does not need to explain any inputs. Baseline score of 4 is appropriate because there is nothing to add beyond the schema's empty parameter list.

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 that the tool provides a French share-capital invoice mention for specific legal forms (SAS/SARL/SA/SCI), with an example format. It distinguishes itself from a Kbis document, but does not use an explicit action verb like 'generate' or 'return'.

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 usage guidance by stating that EI/micro have no capital, implying the tool should only be used for sociétés. It also clarifies that it is 'format only' and not a Kbis, which helps avoid misuse. However, it does not explicitly compare with sibling tools or provide alternative contexts.

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 burden of behavioral disclosure. It mentions the cost ('Paid $0.01 USDC Base x402') and a legal limitation, but it does not describe what the tool actually does (e.g., returns the mention text) or how the optional URL is used. The description is partially transparent but lacks key operational 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?

The description is concise, containing two main sentences plus a cost note. It front-loads the essential mention text and legal reference, then adds a caveat and cost. No unnecessary verbosity, though the cost note could be considered peripheral. Overall well-structured 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 zero-parameter tool, the description covers the legal mention and a caveat, but it does not explicitly state what the tool returns (e.g., the string itself) or how the optional URL factors in. It also does not differentiate from many sibling tools that handle similar legal mentions. Given the simplicity of the tool, it is mostly complete but leaves some operational details unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero defined parameters (schema shows additionalProperties true but no specific params). Baseline for 0 params is 4. The description mentions 'Optional URL' which could imply a parameter, but since no parameters exist, the description does not need to explain parameter semantics further. The baseline applies here.

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 provides a French CGV invoice mention, including the legal reference (C. com. L441-6) and the exact text. It implies its purpose without explicitly using a verb like 'generates' or 'returns', but the context is clear enough for an agent to understand its function. It doesn't explicitly differentiate from siblings, but the specific mention is unique.

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 includes a legal caveat ('A mention does not replace prior communication to the professional buyer') which is a usage note, but it does not provide guidance on when to use this tool versus alternatives. No sibling tools are mentioned, and there is no clear condition for selecting this tool over similar legal mention 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?

No annotations are provided, so the description carries the burden. It discloses a cost ($0.01 USDC Base x402) and a functional limitation (does not prove account existence), which are helpful behavioral traits. However, it does not state whether the tool is read-only, has side effects, or how it handles errors, leaving some behavioral aspects unspecified.

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 well-structured. It conveys the core functionality, a key limitation, and the cost in three short sentences with no unnecessary fluff. The information is front-loaded and easy to scan.

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 checksum validation tool, the description covers the main purpose, a caveat, and the pricing. However, it lacks any mention of the expected input parameter or the output format/return value. Given the schema provides no parameter details, the description is not fully complete for an agent to invoke it correctly without guessing.

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 no defined parameters (only additionalProperties: true), and the description does not mention any input parameter. While the tool name implies an IBAN is expected, the description offers no clarification on the required input format, structure, or optional arguments. This is a critical gap for invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool performs an IBAN ISO 13616 checksum, which is a specific action on a specific resource. It also clarifies what it does not prove, adding precision. It is distinct from sibling tools like iban_fr by being general rather than France-specific, though it doesn't explicitly name the alternative.

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 does not provide explicit guidance on when to use this tool versus other sibling tools. It mentions a limitation ('Does not prove the account exists') but does not indicate scenarios where this tool is preferred or excluded. No alternative tools are referenced, leaving usage context vague.

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 transparency burden. It discloses the cost ($0.01 USDC Base x402) and the absence of an INSEE call, which are important behavioral traits, though it does not mention error behavior or side effects.

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, using three short sentences to convey purpose, external dependency, and cost without any superfluous 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?

There is no output schema, and the description does not specify the return format or expected result of the checksum validation. It also does not mention input format (e.g., SIRET vs SIREN), which could be necessary for correct invocation. The cost and non-INSEE note are useful, but output details are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is empty with no parameters, so there are no parameter semantics to describe. The description does not add parameter details, but this is acceptable given the zero-parameter context.

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 performs a SIRET/SIREN checksum using Luhn / La Poste, and explicitly distinguishes itself from an INSEE call, which is a relevant sibling distinction (e.g., siren_from_siret).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies usage for local checksum validation without calling INSEE, but does not explicitly state when to prefer this over alternatives or provide a conditional context.

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

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

No annotations are provided, so the description must disclose behavior. It mentions a payment of $0.01 USDC Base x402, which hints at a cost but is unclear. It does not state whether the tool is read-only, what it returns, or any side effects beyond 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 concise, three sentences, with the core purpose front-loaded. The legal reference and distinction are useful, and the payment note is brief. 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 zero-parameter tool, it still fails to explain what the tool actually returns (presumably a text snippet), how the optional amount is used, or the significance of the payment. The description is too terse to fully prepare an agent to call it 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?

There are no defined parameters, and the schema is permissive (additionalProperties). The description mentions 'Optional amount', which could imply an optional parameter, but it is not linked to a schema field. This adds slight semantic value beyond the empty schema, but remains ambiguous.

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 specific purpose: generating a French contractual penalty clause based on C. civ. 1231-5, and distinguishes it from the statutory late-payment clause (L441-10). This is clear enough to differentiate from general penalty tools, though it does not explicitly state it 'returns' or 'generates' text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides one exclusion: distinct from statutory late-payment, implying use for contractual clauses. However, it does not explain when to choose this over sibling tools like penalty_text or late_penalties, nor any prerequisites or context.

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

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

With no annotations, the description carries the full burden of explaining side effects, permissions, or return behavior, and it fails to do so. The unexplained 'Paid $0.01 USDC Base x402' is especially problematic because it suggests an unverified financial or external side effect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The first part is short and front-loaded, but the description includes the irrelevant and unexplained 'Paid $0.01 USDC Base x402' text. This extraneous content prevents the description from being clean and purposeful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, no indication of return value, and no explanation of behavior. The legal reference to L441-9 adds context but is not enough for an agent to understand what will happen when the tool is invoked.

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 defines zero parameters, so parameter semantics are largely not applicable; the baseline is 4. However, the schema's additionalProperties: true leaves room for arbitrary inputs, and the description does not clarify what, if anything, should be passed.

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 specific resource—a French invoice purchase-order reference—and mentions a legal usage, but it lacks a verb and never states what the tool actually does with the reference. The appended 'Paid $0.01 USDC Base x402' string adds confusion rather than clarifying the purpose.

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 about when to prefer this tool over the many sibling field tools. 'Usage for identifying the operation (L441-9)' is too vague to help an agent choose between this and related invoice fields, and no alternative tools are mentioned.

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 must disclose behavioral traits. It fails to state whether the tool is read-only, requires authentication, or has side effects. The unexplained 'Paid $0.01 USDC Base x402' is confusing and does not clarify behavior. This is a significant gap for a tool with no annotation support.

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, with the core information front-loaded in the first sentence. The second sentence about payment is extraneous and detracts from clarity, but overall the length is appropriate and the structure is 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 tool with no parameters and no output schema, the description covers the core content (retention periods and legal basis). However, it does not specify the return format (e.g., plain text, structured data) or clarify the payment note. This leaves some ambiguity about what the agent will receive or whether payment is required.

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 schema is an empty object with additionalProperties true, so there is nothing to document. Baseline for 0 params is 4, and the description adds no conflicting information. It correctly does not attempt to describe parameters that do not exist.

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: providing French invoice retention periods (10 years commercial, 6 years tax) with legal references. It distinguishes itself from siblings by focusing on retention, which no other tool mentions. Though it lacks an explicit verb like 'returns' or 'provides', the intent 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?

The description gives no guidance on when to use this tool versus alternatives. There is no mention of use cases, prerequisites, or exclusions. While the name 'conservation' implies retention, the description does not explicitly instruct when an agent should invoke it over other French invoicing 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?

With no annotations, the description carries the full burden. It discloses several behaviors: generating the next AV- number, including a CGI 289 mention, optional reversal, and not reusing cancelled invoice numbers. However, the meaning of 'collable' and the payment statement are unclear.

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 but densely packed with jargon and an unexplained payment sentence. Key terms like 'collable' and 'Paid $0.01 USDC Base x402' are not earned or clarified, making the structure feel cluttered rather than concise.

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 no output schema and no parameters, the description should explain what context is required and what result to expect. It does not clarify how the original invoice is referenced, whether a document is generated, or what the tool actually returns. The payment mention adds confusion rather than completeness.

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 there is no parameter information to clarify. The baseline of 4 applies because no parameter semantics are needed.

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 credit note / avoir tool with specific behaviors like an AV- sequence, CGI 289 mention, original invoice reference, and HT/TTC reversal. However, ambiguous wording such as 'collable' and the out-of-place 'Paid $0.01 USDC Base x402' reduce clarity.

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 guidance is given for when to use this tool versus the many sibling invoicing tools. It does not mention alternatives or conditions that would distinguish credit note creation from related operations.

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, and the description does not disclose any side effects, permissions, data handling, or costs. The cryptic 'Paid $0.01 USDC Base x402' could imply a payment or transaction, but it is not explained, leaving behavioral expectations completely opaque.

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 brief but includes irrelevant and confusing content ('Paid $0.01 USDC Base x402') that distracts from the core subject. The formatting information is fragmented (weekday, long form, label) without clear organization, reducing 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?

While it mentions a date format conversion and a label, the description lacks a complete specification of input/output behavior. It does not explain how the tool handles weekdays, long-form dates, or the 'Date de facture' label, nor does it clarify the L441-9 reference. The unrelated payment note adds noise without context.

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 no defined parameters (schema coverage is 100% with zero parameters), so the baseline of 3 applies. However, the description does not clarify what input is expected (e.g., a date string, an invoice object) despite additionalProperties being true, leaving potential inputs ambiguous.

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 ('French invoice date format') without an explicit verb indicating the tool's action. It shows a format conversion (YYYY-MM-DD → JJ/MM/AAAA) but doesn't clearly state what the tool does (e.g., convert, format, validate). The mention of 'Paid $0.01 USDC Base x402' is unrelated and further obscures the purpose.

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 the many sibling tools (e.g., date handling, invoice formatting). There is no mention of alternatives, prerequisites, or typical use cases. The description is entirely context-free regarding selection criteria.

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 bears the full burden. It mentions a payment/cost ('Paid $0.01 USDC Base x402') but does not clarify side effects, external calls, or whether the tool is read-only. The behavioral description is vague and incomplete.

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 core calculation. The final sentence about payment is somewhat tangential but brief. Overall, it is efficient and does not waste words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description does not explicitly state the return value format, edge cases, or error behavior. While the name and phrasing imply a numeric day count, the lack of explicit output details and the cryptic payment note reduce completeness.

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 is empty, so the description provides the only parameter documentation. It names due_date, as_of, invoice_date, and net_days and explains their relationships. However, it omits types, formats, and optionality, leaving some parameter semantics under-specified.

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 computes calendar days late between due_date and as_of, with an alternative invoice_date + net_days calculation. It distinguishes itself from late_penalties by noting days_late feeds into /v1/late-penalties. A more explicit verb like 'calculate' would improve clarity, but the purpose is understandable.

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 the main computation, an alternative input form, and a downstream usage instruction ('Feed days_late into /v1/late-penalties'). However, it does not explicitly compare against sibling tools or state when not to use this tool, leaving some usage context implicit.

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 or description clarify whether the tool reads, writes, or performs a financial action. The word 'paid' hints at a transaction, but no side effects, permissions, or state changes are disclosed.

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 but includes an unrelated and confusing phrase ('Paid $0.01 USDC Base x402') that adds noise without value. The structure is not well-focused on the tool's actual 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?

The description lacks necessary context for using the tool correctly: no explanation of how disbursements are processed, no output schema, no relationship to the invoicing domain or sibling tools. The odd crypto reference further undermines completeness.

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 is an empty object with additionalProperties true, so no parameters are formally defined. The description vaguely mentions 'optional amount + label' but does not specify names, types, or meaning, leaving parameter semantics undefined.

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 handling 'French disbursements (débours)' with a legal reference (CGI 267) and mentions optional amount and label, giving a partial sense of purpose. However, the trailing phrase 'Paid $0.01 USDC Base x402' is irrelevant and confusing, detracting from clarity.

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 the many sibling tools (e.g., tva_rate, ht_ttc, payment_means). There is no indication of context, prerequisites, or alternatives.

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 carries the transparency burden. The 'Paid $0.01 USDC Base x402' sentence hints at a cost or side effect but does not clearly state whether invoking the tool charges the user, and no other side effects are disclosed.

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 front-loads the legal topic, but the final 'Paid $0.01 USDC Base x402' sentence is cryptic and not clearly tied to the tool's function. Structure is acceptable but the payment note could confuse rather than inform.

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 the tool's legal purpose and trigger condition, but it does not specify what the tool returns (e.g., a mention string) or how to interpret the output. For a simple no-input tool this may be sufficient, but the ambiguous payment sentence and absent output format leave 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 tool has zero specified parameters and an empty schema with additionalProperties true, so there are no parameter meanings to add. The description does not document arbitrary additional properties, but with no declared parameters this is not a significant 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 identifies a specific French legal invoice concept and states the behavior (delivery/service execution vs invoice date, with explicit mention when distinct). It lacks an explicit action verb like 'returns' or 'generates', but the intent is clear from the legal reference and condition.

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 guidance is given for when to prefer this tool over the many sibling invoice-mention tools, nor any 'use when' or 'do not use when' direction. The distinct-date condition implies a trigger, but it is not spelled out as usage guidance.

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

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

No side effects, permissions, or behavioral details are disclosed. The tool could be read-only or mutating, but nothing in the description clarifies this.

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 contains irrelevant information like 'Paid $0.01 USDC Base x402' and is not organized effectively. It is short but not focused or clear.

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 parameters, no output schema, and a vague purpose, the description lacks essential context for an agent to invoke this tool correctly. It does not explain what the tool returns or how the optional number is used.

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 description references an 'optional number' but the schema defines no parameters (additionalProperties true with no named properties). This is a mismatch that leaves input semantics completely unclear.

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 lists possible document types and an optional number but does not clearly state what the tool does (e.g., generate, return, validate). The phrase 'CGI 289 document title:' is cryptic and lacks a verb or clear resource.

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 its many siblings (e.g., invoice_numbering, proforma, etc.). No explicit conditions or use cases are described.

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 that it does not fetch a live calendar, which is a relevant behavioral trait given the tool's dependence on calendar data. However, it omits other behavioral details like side effects or permissions, and includes an irrelevant payment note that detracts from transparency. No annotations are provided to supplement this.

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 not concise; it includes an irrelevant and confusing phrase 'Paid $0.01 USDC Base x402' that does not relate to the tool's function. The core information about due date calculation and the no-live-fetch limitation is present but buried among extraneous details.

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 and explicit parameters, the description should provide enough context to invoke the tool correctly. It fails to specify the expected input structure or return format, leaving the agent without a clear calling convention. The mention of invoice_date and net_days is a start but insufficient for complete usage.

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 is empty with no defined properties, and the description mentions invoice_date and net_days but does not formally document them as parameters or explain their types, formats, or constraints. The agent receives no meaningful information about what arguments to pass, making parameter semantics nearly opaque.

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 computes French invoice due dates from invoice date and net days, and also mentions the related next_open_day calculation. This is a specific verb and resource, distinguishing it from sibling tools like holidays or open_days, though the dual mention slightly muddles the primary purpose.

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 explicit guidance on when to use this tool versus alternatives. The note 'No live calendar fetch' hints at a limitation but does not direct the agent to choose this tool over others, such as holidays or open_days, for specific scenarios.

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 exist, so the description carries the full burden. It usefully discloses the two interpretations (statutory 45-after-month-end vs alternate +45-then-EOM) and the stipulation requirement, which is real behavioral context. However, it ends with the irrelevant 'Paid $0.01 USDC Base x402' line, which adds noise rather than behavior. It also never states what the tool returns. A 3 reflects partial disclosure with a distracting non-sequitur.

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 core explanation is tight and front-loaded with the legal basis and both readings, but the final sentence 'Paid $0.01 USDC Base x402' is unrelated noise that wastes a clause and dilutes focus. Three useful sentences followed by one irrelevant fragment — efficient but not clean.

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 explains the concept and its legal context well, covering both statutory and alternate readings. But it never discloses what the tool outputs (e.g., a formatted due-date string to insert), and with no annotations or output schema, that gap is the agent's only missing piece. The USDC noise further reduces completeness.

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?

Zero parameters, so baseline 4 applies. The description explains the meaning of the 45-day EOM concept itself, which is the closest thing to parameter semantics for a parameterless tool. Nothing more is needed.

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 concept — French 45-days-end-of-month due date — with legal citation (L441-10 I derogation) that clearly distinguishes it from sibling 'due_date'. The verb is implicit (the tool represents/produces a due-date term) but the resource and scope are unambiguous. It earns a 4 because it is specific and identifiable, though it never states an explicit 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?

No guidance on when to use this tool versus alternatives. With siblings like 'due_date', 'payment_term_max', and 'days_late', the description never names a condition that selects this tool or an alternative to prefer. 'Must be stipulated' is a legal requirement about the term, not usage direction. An agent gets no routing help.

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 burden of behavioral disclosure. It mentions that L441-10 penalties accrue without a reminder and notes it is 'usage' rather than statutory, adding context about the nature of the output. However, it does not describe what the tool actually returns (e.g., a list, a string, a calendar object), nor any side effects or auth requirements. The cryptic 'Paid $0.01 USDC Base x402' adds confusion rather than clarity. Overall, it provides some behavioral context but leaves significant 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 short and front-loaded with the main purpose, but it includes extraneous and confusing elements such as 'Paid $0.01 USDC Base x402' which does not contribute to understanding the tool's function. The sentence about penalties is tangential to the core purpose. The structure is a run-on with mixed information, reducing clarity 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?

Given that there are no annotations, no output schema, and no parameters, the description is the only source of context. It fails to explain what the tool returns or how the agent should use the result. The mention of penalties and the 'usage' caveat provide some context, but an agent would still not know what to expect from the call. This is incomplete for a tool with no other documentation.

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 input schema is empty, so the schema already covers everything. The description does not need to explain parameters. Per the guidelines, a baseline of 4 is appropriate when there are no parameters, as the description adds no additional parameter semantics but also doesn't need to.

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 suggested FR B2B dunning calendar with specific intervals (J+1 / J+8 / J+15) and explicitly notes it is not a statutory timetable. This differentiates it from likely siblings like late_penalties or payment_term_max, though it doesn't explicitly say 'returns a schedule'. The purpose is evident from the phrasing.

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 some usage context by stating it is a 'suggested' calendar and 'not a statutory timetable', implying when not to use it (for legal requirements). However, it does not name any alternative tools or explicitly state when to use this tool over others, leaving the agent to infer from the sibling list. This is partial guidance but not 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?

No annotations are provided, so the description carries the full burden. It includes odd details like 'Paid $0.01 USDC Base x402' and 'Collable ‘Ne pas comptabiliser une seconde fois.’' without explaining their meaning or the tool's side effects. This leaves the behavioral implications unclear, such as whether the tool modifies an existing invoice or creates a new record.

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 relatively brief, but it includes extraneous and confusing elements such as 'Paid $0.01 USDC Base x402' and ungrammatical phrasing like 'Collable.' These distract from the core message and reduce structural 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 that the tool has no parameters and no output schema, the description should be self-sufficient. However, it is cryptic and does not clearly explain the tool's purpose or behavior, leaving gaps in understanding that an agent would need to infer or research.

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 no defined parameters (additionalProperties is true but no properties are listed), and schema coverage is 100%. Since there are no parameters to describe, the baseline score of 4 applies, and the description is not required to explain parameter semantics.

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 'French invoice duplicata' with the same original number stamped DUPLICATA, and explicitly differentiates it from a new L441-9 number and a credit note. This provides some clarity, but it does not clearly state the action or function of the tool (e.g., creating, generating, or marking a duplicate), leaving the purpose somewhat ambiguous.

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 negative guidance by stating it is 'Not a new L441-9 number and not a credit note,' which helps distinguish it from some sibling tools. However, it does not explicitly state when to use this tool versus alternatives, such as the exact conditions under which a duplicata should be issued.

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 some behavioral traits: it performs no registry lookup and is paid ($0.01 USDC Base x402). However, it does not clarify whether the tool is read-only, idempotent, or whether it has any side effects beyond the stated payment. The disclosure is partial but not 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 brief and information-dense, with no redundant filler. Phrases like 'Size in, dates out' are compact and memorable. The payment and no-lookup notes add relevant behavioral context without bloating the text.

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 gives the core rule and key dates, which is likely sufficient for a simple helper tool. However, it omits the output shape, how the size input is interpreted, and any edge cases such as company classifications. It is complete enough for a rough understanding but not 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 input schema is empty with additionalProperties true, so no formal parameters are defined. The description references an implicit 'size' input but does not specify the expected format, allowed values, or how to supply it. This leaves significant ambiguity for callers.

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 a French e-invoice calendar and indicates that it returns obligation dates based on company size. The phrases 'Size in, dates out' and the specific date thresholds make the core purpose understandable. It loses one point because the wording is slightly compressed and could be misread.

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 does not explicitly state when to use this tool versus alternatives. It gives a hint with 'No registry lookup' but does not mention any sibling tool or provide selection criteria. The payment note is present but not framed as a usage condition relative to other 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?

Beyond the standard format description, the tool discloses that it is paid ($0.01 USDC Base x402) and that it does not perform customs lookup. These are relevant behavioral traits that an agent needs to know before calling.

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, covering the format rules, the variation for SIRET, the limitation (no customs lookup), and the cost in three sentences. No superfluous words are used.

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 there is no output schema and no parameters, the description provides sufficient context: the input is implied (SIREN/SIRET), the output format is described, and the limitation and cost are stated. It is complete enough for an agent to understand the tool's 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 has zero parameters, so the baseline is 4. The description compensates by explaining that the tool accepts a SIREN or SIRET input and returns the corresponding EORI format, effectively describing the implicit input semantics.

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: it converts a SIREN into an EORI number (FR + SIREN) and a SIRET into the establishment form (FR + SIRET). It also explicitly notes that it is format-only and not a customs lookup, which distinguishes it from other potential tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides guidance by specifying that the tool performs formatting only and does not perform customs lookup. This clarifies when to use it (for formatting) and when not to (for actual lookup). Although it does not mention sibling tools, the instruction is clear and actionable.

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 carries full burden for disclosing side effects. It does mention a $0.01 USDC payment, which is a notable behavioral trait, but it does not state whether the tool is read-only or has other destructive side effects. The disclosed cost is partial 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 concise, delivering the essential information in a single sentence. It includes the legal basis, the two possible output texts, and the payment requirement without any superfluous content.

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 no input parameters and no output schema, the description is complete. It explains the output format via example strings and mentions the cost, providing everything an agent needs to decide 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 tool has zero parameters, and the description correctly provides no parameter details. According to the rubric, 0 params warrants a baseline of 4, and the description does not conflict with this.

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: generating a French early-payment discount mention with exact legal references and example text. It specifies the exact output strings and the associated payment, leaving no ambiguity about what the tool does.

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 does not explicitly indicate when to use this tool versus alternatives. It gives no comparison to sibling tools or conditions under which this mention should be generated, leaving the agent to infer usage context from the French law references 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 burden. It discloses a paid operation ($0.01 USDC Base x402) and clearly states the output is a VAT exemption mention. It does not mention side effects or permissions, but for a simple label-generation tool this is adequate.

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, packing legal references, a distinction from the sibling tool, and a payment note into three short sentences. No redundant words 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 simple nature of the tool and absence of parameters or output schema, the description provides enough context to understand its purpose and when to use it. The legal references add useful specificity, though it does not describe the exact output format or text.

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 there are no parameter details to document. The schema is empty and the description is not required to explain parameters; a baseline score of 4 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 identifies the tool as generating a French VAT exemption mention, specifying the legal bases for extra-EU exports (CGI 262 I) and intra-EU supplies (CGI 262 ter I). It is immediately distinguishable from the sibling reverse-charge 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 explicitly contrasts this tool with /v1/autoliquidation, indicating when this tool should be used instead of the reverse-charge alternative. It does not elaborate on broader usage contexts, but the core selection guidance is present.

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?

There are no annotations and the description does not disclose side effects, return format, or behavior. The 'Paid $0.01 USDC Base x402' text appears unrelated and potentially injected, undermining 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 short but includes extraneous and unrelated content such as 'Paid $0.01 USDC Base x402' and 'Not a tax ruling', which detracts from the core, already vague message.

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 tool this description is still incomplete: it does not state what the output will be, whether it returns a mention string, a boolean, or a calculation result, leaving an agent unable to predict tool 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 tool has zero parameters and schema coverage is effectively complete, so the baseline of 3 applies. No parameter-specific description is needed.

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 does not state a clear action or resource. It mentions 'thresholds' and 'statutory invoice mention' but lacks a verb like 'calculate' or 'get', and the appended 'Paid $0.01 USDC Base x402' is irrelevant and confusing.

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 the many sibling tools. The disclaimers 'Not a tax ruling' and the unrelated payment text do not clarify usage.

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

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

No annotations are provided, so the description carries the full burden of disclosing side effects and costs. It does disclose a payment of $0.01 USDC on Base, which is a cost. However, it does not indicate whether the tool is read-only, modifies data, or has any other side effects. Given the lack of annotations, this is a significant gap.

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, with three clear sentences: purpose, logic, and cost. It contains no superfluous information and is well-structured, making it easy to parse. The clarity is slightly reduced by the cryptic notation '→ expiry' but overall it is 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 tool, the description provides essential information: purpose, differentiation from legal warranty, logic, and cost. However, it does not describe the output format (e.g., the expiry date format) or any potential variations or edge cases. Given the low complexity, it is mostly complete but lacks some details.

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 no parameters, but the description mentions 'months' and 'delivery_date' and explains their relationship (months added to delivery_date to compute expiry). This adds meaning beyond the empty schema, though it is not structured and does not clarify parameter types or requiredness. The description partially compensates for the lack of schema information.

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 handling the French commercial warranty mention, referencing the legal article (C. conso L.217-21) and distinguishing it from the legal warranty (garantie_legale). The purpose of computing an expiry date from months and delivery_date is implied but not explicitly stated with a verb, so it is clear but not fully explicit.

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 explicitly states that this is distinct from the 2-year legal warranty, which helps an agent choose between this tool and garantie_legale. However, it does not provide explicit conditions like 'use when the user asks for commercial warranty' or contrast with other sibling tools. The usage context is implied but not fully spelled out.

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 explains the core behavior: optional delivery_date produces an expiry date based on a 2-year period. However, it does not disclose whether the tool has side effects, and the phrase 'Paid $0.01 USDC Base x402' is ambiguous and potentially implies an unexpected payment-related 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 legal warranty explanation is concise and front-loaded, but the final sentence 'Paid $0.01 USDC Base x402' is unrelated to the tool's function and creates confusion. Removing or clarifying that string would make the description more effective.

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 gives enough context for a basic legal warranty expiry calculation, but it omits the output format or return value shape. The ambiguous payment string also leaves room for misinterpretation, so the description is not fully complete on its own.

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 no formal properties, but the description mentions 'optional delivery_date' as an input. This adds meaning beyond the empty schema, but it does not specify the expected date format, and the schema's additionalProperties: true makes the accepted input surface unclear.

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 this tool calculates the French legal warranty of conformity: 2 years from delivery for consumer goods. It distinguishes itself from commercial warranty tools by referencing the specific legal rule and consumer-only applicability.

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 it: for consumer goods legal warranty calculations, and explicitly says it does not apply to professional buyers. It does not explicitly name alternative tools like garantie_commerciale, but the scope is clear enough for most selection 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?

With no annotations, the description carries full transparency burden. It discloses that no live fetch occurs and that payment of $0.01 USDC is required, but omits auth, error behavior, and output shape.

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?

Extremely concise with key facts front-loaded: purpose, legal reference, options, and constraints. Every sentence adds distinct 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?

Minimal context: no output schema, no parameter documentation, and no explanation of how to select 2026 vs 2027 or the Alsace extras. For an agent to call correctly, more detail is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema is empty and no parameters are documented, so the baseline is 4. The mention of optional Alsace-Moselle extras is ambiguous because no parameter is declared, but it does not contradict the empty 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?

Clearly identifies the tool as returning French public holidays for 2026 or 2027, with legal reference. It does not state an explicit verb like 'get' or 'list', but the resource and scope are 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?

Mentions 'no live fetch' and cost, but does not explain when to choose this tool over siblings like alsace_holidays or how to request the optional Alsace-Moselle extras. No alternative or conditional guidance is given.

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 burden. It includes a caveat ('Not a tax ruling') and a note about payment ('Paid $0.01 USDC Base x402'), but does not mention side effects, return format, or destructive actions. The transparency is partial.

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, well-structured, and free of unnecessary words. Each sentence adds relevant information: purpose, parameter guidance, and a caveat. No 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?

Given that there is no output schema, the description adequately covers the tool's purpose, input requirements, and a caveat. It could be more complete with an example or explicit return type, but the current level is sufficient for an agent to understand 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 input schema has no defined parameters, but the description mentions two likely inputs (amount_ht and amount_ttc) and clarifies that exactly one must be passed. However, it does not specify how to indicate the tax rate or any other possible parameters, leaving some ambiguity.

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 converts French HT to TTC and vice versa using CGI indicative tax rates, which is a specific and unambiguous purpose. It also distinguishes itself from sibling tools like tva_rate or vat_key by focusing on conversion rather than rate lookup.

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 guidance on parameter usage ('Pass exactly one of amount_ht or amount_ttc') but does not explicitly state when to use this tool over alternatives. However, the purpose itself is self-contained, implying usage when conversion is needed.

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?

Mentions a limitation about account existence, which is helpful, but the strange 'Paid $0.01 USDC Base x402.' sentence suggests behavior unrelated to the tool and could mislead the agent. No annotations are present to offset this.

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 but includes a completely extraneous and confusing sentence about payment. This unnecessary addition harms conciseness and structure.

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 mentions structure and checksum but omits the actual function (e.g., whether it validates, formats, or extracts). The payment sentence is irrelevant and makes the overall context incomplete and potentially misleading.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no defined parameters in the schema (empty object with additionalProperties true). The description does not explain what input the tool expects (e.g., an IBAN string), but since no parameters are declared, the lack of detail is less critical.

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 says 'French IBAN structure: 27 chars...' but does not clearly state that the tool validates or checks an IBAN. The added sentence 'Paid $0.01 USDC Base x402.' is unrelated and confusing, further reducing clarity.

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 one caveat ('Does not prove the account exists') but gives no guidance on when to use this tool versus alternatives. The irrelevant payment sentence adds no usage direction.

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?

There are no annotations, and the description fails to disclose whether the tool is read-only, whether it has side effects, or what output it produces. The unexplained phrase 'Paid $0.01 USDC Base x402' is confusing and obscures rather than clarifies the tool's behavior. No side effects, errors, or state changes are mentioned.

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, but the inclusion of 'Paid $0.01 USDC Base x402' is extraneous and unrelated to the stated purpose. The legal reference 'L441-10' and the computation rule are packed together without clear structure. Removing the payment fragment would improve conciseness.

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 omits the return format, output schema, and any error or edge-case behavior. It does not explain how the input date is used or what value the caller receives. The mysterious payment sentence adds no contextual value and leaves the tool's contract incomplete.

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 declares zero parameters, yet the description says it 'Accepts due_date or invoice_date + net_days,' which contradicts the schema and leaves no formal parameter definitions. This inconsistency makes the actual inputs ambiguous. The description adds no clarity about types, formats, or required versus optional fields.

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 that the tool determines when calendar-day late-payment interest begins: the day after the due date, and that no reminder is required. The legal reference L441-10 and the tool name 'interest_start' reinforce this purpose. However, it lacks an explicit verb such as 'calculate' or 'return'.

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 does not explain when to use this tool versus sibling tools like late_penalties, penalty_text, or due_date. It provides no alternatives, conditions, or scenarios. The only hint is the 'without a reminder' clause, but it is not developed into actionable 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 must disclose side effects or read-only behavior. It mentions nothing about what the tool does internally or externally, and the confusing phrase 'Paid $0.01 USDC Base x402' introduces potential hidden behavior without explanation.

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 unnecessarily verbose and includes extraneous, nonsensical content ('Paid $0.01 USDC Base x402') that should be removed. Key information is buried amidst irrelevant statements.

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 does not fully explain the output or behavior of the tool. It mentions currency codes and legal tender but omits critical details like return format or conditions, leaving the agent with an incomplete picture.

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 an empty schema, so the description is not required to clarify parameters. However, it also does not confirm that no input is expected, leaving a minor 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 vaguely indicates the tool deals with French invoice currency, but includes bizarre and irrelevant text like 'Paid $0.01 USDC Base x402' that obfuscates the core purpose. It does not explicitly state what the tool does (e.g., returns or validates currency).

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 explicit guidance on when to use this tool versus alternatives. The phrase 'Offline subset, no FX rate' hints at constraints but does not clarify selection criteria or relationships with 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?

No annotations are provided, so the description carries the full burden. It discloses that the tool is paid ($0.01 USDC Base x402) and that it returns a number, but it does not explicitly state whether there are side effects or state changes. Given the helper nature, it is likely read-only, but this is not confirmed.

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 concise, consisting of two sentences that efficiently convey purpose, behavior, and cost. No unnecessary words are used, and it is well-structured for quick understanding.

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 provides the essential purpose and behavior, but given that there is no output schema, it lacks detail on the exact format of the returned number or the nature of the 'statutory rules'. This leaves some ambiguity for the agent about the 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 input schema defines no parameters, leaving the description to compensate. It mentions 'last_number' as an input, which gives some meaning, but it does not describe the format, requirements, or any other potential parameters. This is partial coverage at best.

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 as a French invoice numbering helper, with the specific functions of providing a unique chronological sequence with no gaps and returning the next number based on the last number and statutory rules. This is distinct from the other sibling tools, which cover different aspects of French business documentation.

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 (when generating the next invoice number) and mentions the statutory basis (C. com. L441-9). However, it does not explicitly state when not to use it or compare it to alternative tools, leaving some 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?

No annotations are provided, so the description carries the full burden. It explains the calculation behavior but includes an unexplained 'Paid $0.01 USDC Base x402' phrase that could mislead an agent into thinking payment or blockchain interaction is involved. Side effects, authentication, or rate limits are not addressed.

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 core explanation is concise and front-loaded, but the trailing 'Paid $0.01 USDC Base x402' is extraneous and unrelated to the tool's apparent purpose. Removing or explaining that phrase would make the description cleaner.

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 provides useful context: legal reference, geographic scope, holiday years, and the rollover rule. However, it does not explain inputs, outputs, or how the paid phrase relates to the tool, leaving some ambiguity for a complex legal/date calculation 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 tool has zero parameters and the schema is essentially empty, so there are no parameter semantics to document. The description adds context about the legal rule and scope, 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 clearly identifies the tool as calculating French 'jours francs' under C. proc. civ. 642 and specifies the core rule (start day excluded, weekends/holidays roll to next open day). It is distinct enough from siblings like holidays and open_days, though it does not explicitly contrast itself with them.

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 usage for computing jours francs in metropolitan France for 2026–2027, but it does not explicitly state when to prefer this tool over related siblings such as open_days or holidays. The odd appended payment sentence further muddies usage guidance.

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

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

No annotations are provided, and the description does not disclose what the tool does, its side effects, or its output. The 'Paid $0.01 USDC Base x402' fragment is inexplicable and does not clarify 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 short but contains an irrelevant and confusing sentence about payment and blockchain, which detracts from clarity. The structure is not logical and lacks a clear subject-verb-object flow.

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 no parameters, the description should explain what the tool does, but it leaves the function ambiguous. It does not specify whether it generates, validates, or translates the language mention, nor what outputs are expected.

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 schema coverage is vacuously 100%, yielding a baseline of 3. The description adds no parameter information because none exist, and it does not contradict the empty 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 references 'French invoice language mention' and the Toubon law, but lacks a clear verb or action, and the trailing phrase 'Paid $0.01 USDC Base x402' is nonsensical and obscures the purpose. It does not clearly distinguish this tool from siblings like 'mention_fields' or 'retractation'.

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 explicit guidance on when to use this tool versus alternatives. The mention of B2C and B2B defaults is vague and not actionable, and no conditions or contexts are 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?

The description discloses that it does not fetch live ECB rates and uses a default MRO of 2.40%, which is transparent. However, the mention of 'Paid $0.01 USDC Base x402' is unexplained and confusing, reducing overall clarity about the tool's actual behavior. No annotations exist to supplement.

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 but poorly structured. Legal references and formula are crammed together with an unrelated payment note. The 'Paid $0.01 USDC Base x402' sentence is a distraction and makes the description feel disorganized.

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 legal context and a formula but lacks essential details: what the output looks like, how inputs are supplied, and when to use this tool over siblings. The incomplete parameter semantics and missing usage guidance make the description inadequate for an agent to confidently 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 defines no parameters, so the description must carry the burden. It names 'amount_ttc' and 'days_late' but does not explain their types, units, or expected formats. It also introduces the default MRO rate without clarifying how it is used. This is insufficient for reliable invocation.

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 that it computes French late-payment interest (BCE MRO+10pts) and a fixed 40€ indemnity under D.441-5, based on amount_ttc and days_late. This is a specific calculation purpose that distinguishes it from sibling tools like penalty_text or dunning_steps.

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 guidance on when to use this tool versus alternatives. It mentions 'No live BCE fetch' but does not advise when a user should prefer this static-rate version over a tool that fetches live rates. Usage context is missing.

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, and the description does not disclose any behavioral traits such as read-only, destructive, or side effects. The mention of pricing is irrelevant to 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 brief but cryptic and poorly structured, mixing functional intent with payment details. It is not clear or well-organized.

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 or expected return format is described. The tool's purpose and capabilities are not sufficiently explained for an agent to invoke it 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 has 0 parameters, so schema coverage is trivially 100%. The description adds no meaningful parameter semantics, but there is nothing to document. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The verb 'Extra' is unclear (likely a typo for 'Extract' or 'Get'), and the resource 'French invoice mentions by legal form' is vague. It does not clearly distinguish from sibling tools like 'rcs_mention' or 'siren_from_siret'.

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 on when to use this tool versus alternatives. The phrase 'On top of /v1/mention-fields' is not a sibling reference and does not clarify selection criteria.

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 that it is format-only and does no math, which is useful, but it does not explain the output format, return value, or any side effects. The inclusion of 'Paid $0.01 USDC Base x402' is confusing and unexplained, detracting from 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 short and front-loaded with the core purpose, but the sentence 'Paid $0.01 USDC Base x402' is extraneous and seems unrelated to the tool's functionality. It adds noise and reduces overall conciseness.

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 no parameters and no output schema, the description states the purpose and format but does not specify the return type or format of the output. The payment note is ambiguous and could mislead an agent. It is adequate but not complete for a clear 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?

The tool has zero parameters, so the schema provides no parameter documentation. The description adds meaning by listing the content of the line (designation, quantity/unit, unit price HT), which clarifies what the tool produces. With no parameters, a baseline of 4 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 function: it defines a French invoice line with designation, optional quantity/unit, and unit price HT, and explicitly says it is format-only with no line-total math. This distinguishes it from sibling tools that handle calculations or other invoice aspects.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies usage for formatting lines rather than computing totals ('Format only, no line-total math'), but does not name specific alternatives or give explicit when-to-use/when-not-to-use guidance. The siblings list exists but no direct reference is made.

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 significant behavioral trait—the $0.01 USDC Base x402 payment requirement—and notes the exclusion for professional buyers. However, it does not describe the output format or any side effects, though the tool's simplicity reduces the need for more detail.

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, using four short sentences to convey purpose, usage condition, input instructions, and cost. No extraneous information is included, and all sentences contribute to the agent's understanding.

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 text-generation tool, the description provides all necessary context: legal basis, applicability, input guidance, exclusions, and cost. The absence of an output schema is acceptable because the tool's output is likely a standard text snippet, and no further details are required.

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 is empty, so the description carries the full burden of explaining parameters. It states to pass the mediator's name and URL, providing semantic meaning, but does not specify formal parameter names, types, or required status, leaving some ambiguity for the agent.

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: generating a French consumer mediator mention per C. conso L.612-1. It specifies when it is required (B2C) and distinguishes it from other legal mention tools, making its function 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 provides explicit usage conditions: required for B2C, not applicable to professional buyers, and instructs to pass the mediator's name and URL. This gives clear when-to-use and when-not-to-use guidance, along with cost 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 provided, the description carries the full burden of disclosing behavior. It does disclose the cost ($0.01 USDC Base x402) and the basic call pattern ('No lookup', JSON in, list of required ids out), which is useful. However, it does not explicitly state whether the tool is read-only, whether it has side effects, or how payment is handled, leaving some behavioral uncertainty.

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 concise, with each sentence contributing distinct information: the purpose, the input/output contract, the fact that no lookup is involved, and the cost. There is no redundant or filler content. It is well structured for a quick agent reading.

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 leaves important context missing for an agent to call the tool successfully. It does not explain what fields must be present in the input JSON, how the output IDs relate to the legal mention fields, or what happens on invalid or missing data. The payment mechanism is mentioned but not detailed, so the overall operational context is incomplete.

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 formal parameters and no schema properties, so there are no parameter details for the description to explain. The description still adds value by stating that the input is JSON and the output is a list of required IDs. It does not enumerate expected JSON keys, but because there are no declared parameters, the baseline for this dimension is high.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool provides a checklist of French invoice/quote legal mention fields and references the relevant legal texts (L441-9, L441-10, 293 B). It also specifies input/output as JSON in and list of required ids out, making the core purpose clear. It does not use a strong verb like 'returns' or 'generates', but the meaning 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?

The description does not explain when to use this tool versus any of the many sibling tools, such as ht_ttc, penalty_text, or quote_validity. The phrase 'No lookup' hints that this is not a lookup service, but it gives no direct guidance on the appropriate situation for invoking it. There is no mention of prerequisites or when it should be avoided.

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, and the description does not clarify side effects, authentication, or output behavior. The phrase 'Paid $0.01 USDC Base x402' is ambiguous and may imply a payment but is not explained.

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 but disorganized, mixing the footer purpose, CGI rate reference, parameter instructions, and an unexplained payment phrase in a way that 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 description omits essential context such as expected inputs, output format, relationship to similar tools, and the meaning of the payment reference, making it incomplete for reliable use.

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 declares no parameters, but the description instructs passing amount_ht or amount_ttc. These are not defined in the schema, and no types, formats, or constraints are provided, creating a significant mismatch.

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 indicates the tool produces a French invoice footer with HT, VAT, TTC, and a 'Net à payer' amount, but it lacks an explicit verb such as 'generate' or 'compute' and includes unclear references like 'collable' and 'Same CGI rates as /v1/ht-ttc'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives the instruction to pass exactly one of amount_ht or amount_ttc, but it does not explain when to use this tool versus sibling tools or provide clear context for the /v1/ht-ttc reference.

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

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

The description discloses a key behavioral trait: the tool is paid ($0.01 USDC Base x402). It also explains the computation logic (skips weekends and specific holidays, optional regional extras). Since no annotations are provided, the description takes on full responsibility for transparency, and it does so adequately, though it does not explicitly state whether it has side effects.

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 begins with the primary purpose and includes essential details (holiday law reference, year range, optional extras, and cost). It is tightly written with no redundant information, making it easy to parse quickly.

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 input schema and output schema, the description is incomplete. It explains what the tool calculates but does not specify how to pass the required dates or how the result is returned (format, type). Without this information, an agent cannot reliably invoke the tool despite the clear purpose.

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 is empty with additionalProperties true, so the description is the only source of parameter information. It mentions 'between two dates' and 'optional Alsace-Moselle extras' but does not define parameter names, types, or formats (e.g., start_date, end_date, region). This is insufficient for an agent to construct a valid call.

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 function: an inclusive count of open days between two dates, skipping weekends and L.3133-1 holidays for French metropolitan areas, with an optional Alsace-Moselle variant. It specifies the exact scope and even includes the payment amount, leaving no ambiguity about what operation is performed.

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 (whenever a French open-day count is needed) but provides no explicit guidance on alternatives or conditions. Sibling tools like 'holidays' or 'jours_francs' exist, but there is no comparison or direction on when to choose this tool over them.

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. It states the tool is a footer and clarifies numbering, but the line 'Paid $0.01 USDC Base x402' is cryptic and could imply side effects, yet it is not explained. The description does not disclose what output the tool produces (e.g., text, formatting) or any state changes.

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 front-loads the core purpose (footer Page X/Y). However, the inclusion of 'Paid $0.01 USDC Base x402' is extraneous and likely unrelated to the core function, adding noise without 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?

Given no parameters, no output schema, and no annotations, the description is the sole source of information. It does not explain how the agent should use this tool in an invoice-generation flow, what inputs it relies on from context, or what the expected output format is beyond the literal text. This is insufficient for correct 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?

The tool has zero parameters, so there is no semantic gap to fill. The description does not need to elaborate on parameters, and the baseline of 4 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 identifies the tool as a French multi-page invoice footer and explains the Page X/Y format, distinguishing it from invoice numbering (L441-9). However, it does not explicitly name or differentiate from sibling footer-related tools, so it misses the full clarity bar.

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 simply describes what it is without stating conditions or exclusions. An agent has no direction on when this should be invoked.

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 does not disclose any behavioral aspects such as side effects, permissions, or return format. The inclusion of 'Paid $0.01 USDC Base x402' is entirely opaque and likely irrelevant, and 'Collable string' is unclear. With no annotations to supplement, transparency is poor.

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 not concise—it includes extraneous and cryptic content such as 'Paid $0.01 USDC Base x402' and the possibly misspelled 'Collable string'. These additions do not contribute to understanding and should be removed, making the overall structure cluttered.

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 simple nature of the tool (likely returning a string), the description should clearly state the output. It does not provide a sample or clarify the exact string format. The ambiguous notes and lack of explanation for 'Collable' leave the context incomplete, requiring the agent to make assumptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters defined in the schema, and the description does not clarify any inputs. The phrase 'Default virement' misleadingly implies that a parameter might exist to select a different payment means, creating ambiguity. The irrelevant 'Paid $0.01 USDC Base x402' further detracts. Since there are no params, the baseline is 4, but the implied input and confusing notes lower it to 3.

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 a French invoice means-of-payment mention, listing the exact options (virement, chèque, CB, espèces, prélèvement, LCR) and a default (virement). It is specific and distinct from sibling tools, though it lacks an explicit verb like 'generate' or 'return'. The phrase 'Collable string' is ambiguous but does not obscure the core purpose.

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 guidance on when to use this tool versus alternatives is provided. The mention of L441-9 gives legal context, but there is no differentiation from other invoice-related sibling tools, leaving the agent to infer applicability. The default value hints at usage but does not specify 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?

No annotations are provided, so the description bears full responsibility for behavioral transparency. It discloses that the tool relates to a statutory ceiling and that the term is not recommended, but does not state whether the tool is read-only, has side effects, or returns a value. The phrase 'Paid $0.01 USDC Base x402' is confusing and suggests an unrelated payment or test, which obscures rather than clarifies 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 core information (statutory ceiling and legal reference) is concise and front-loaded. However, the sentence 'Paid $0.01 USDC Base x402' appears irrelevant and confusing, detracting from the structure. 'Not a recommended term' is somewhat useful but not essential. Overall, the description is brief but contains an unnecessary element.

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 (no parameters, no output schema), the description still lacks completeness because it does not state what the tool actually returns or how it functions. It describes the legal rule but not the tool's action (e.g., returning a value, checking a term, or providing a reference). The confusing 'Paid' phrase adds ambiguity. An agent would be uncertain about how to use the tool's 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?

There are no parameters in the input schema (0 parameters, 100% schema coverage). Since there is nothing to document, a baseline score of 3 is appropriate. The description does not need to explain parameter semantics because none exist.

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 that the tool provides the statutory ceiling for French B2B payment terms (60 days or 45 days end-of-month). It also indicates it is not a recommendation. However, it does not explicitly say whether the tool returns the maximum value, validates compliance, or serves as a reference, leaving some ambiguity about its exact function.

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 does not provide guidance on when to use this tool compared to sibling tools. It mentions the statutory ceiling and that it is not a recommended term, but does not specify scenarios such as checking payment term compliance or calculating the maximum allowed duration. There is no explicit 'use this when' 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?

No behavioral traits are disclosed: there is no mention of side effects, read-only status, output format, or error behavior. The odd 'Paid $0.01 USDC Base x402' fragment actively confuses rather than clarifying what the tool does or returns.

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 brief but includes irrelevant and unexplained content such as 'Default MRO 2.40% H2 2026' and 'Paid $0.01 USDC Base x402,' which should be removed for clarity. The statutory references are useful, but the extraneous tokens make the description unfocused.

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 provides some statutory context and rate info but fails to fully explain what output is generated or when to select this tool. The unrelated 'Paid $0.01 USDC Base x402' sentence adds confusion and is not integrated into any coherent tool 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 tool has zero parameters, so there is little to add beyond the empty schema. 'No amount required' gives a hint about a possible amount parameter, but since no parameters exist, it adds limited meaningful parameter context.

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 generating statutory French invoice penalty mention strings (L441-10 / D.441-15) with rate and indemnity details, so the general purpose is recognizable. However, it lacks an explicit verb and is muddled by irrelevant text like 'Paid $0.01 USDC Base x402,' which obscures the intended function.

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 such as late_penalties or interest_start. The fragments 'No amount required' and 'Default MRO 2.40% H2 2026' hint at behavior but do not explain conditions or selection criteria.

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 payment of $0.01 USDC Base x402, indicating a cost per call, but the payment mechanism is cryptic and no other side effects are mentioned. Since no annotations are present, this partial disclosure is the only 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 brief and to the point, but the phrase 'collable mention' is unclear and the payment note is terse. It could be more readable with clearer terminology, but overall it is not overly verbose.

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 lacks a defined input schema and output schema, so the description is the sole context. It provides some background (French invoice, continuous services, CGI 289) but omits details on expected inputs, output format, and how the payment relates to usage, leaving the agent under-informed.

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 defines zero parameters, yet the description implies inputs ('from + to dates'). This mismatch leaves the agent without a clear way to specify the required dates, and the empty additionalProperties schema offers no structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool creates a French invoice billing period mention for continuous services (CGI 289), specifying from and to dates. This gives a clear domain and use case, though the term 'collable' is ambiguous.

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 reference sibling tools or provide any decision criteria, leaving the agent to guess based on 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?

The description discloses non-behavioral aspects like 'No subscriber lookup' and the payment cost, but it does not explain behavior on invalid input, error handling, or any side effects. Since no annotations are provided, the description carries the full burden, and it only partially covers behavioral expectations.

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, packing essential information into a few short phrases. It covers the core transformation, output types, and exclusions without any redundant words or unnecessary detail.

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 open schema and lack of output specification, the description is incomplete. It does not state the expected input format, the output structure (e.g., JSON fields), or handle edge cases. For a tool with no parameters defined, this lack of context makes it difficult for an agent to use 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 input schema is an open object with additionalProperties allowed, but no specific parameters are defined. The description does not mention what input the tool expects (e.g., a phone number string, country code, etc.), leaving parameter semantics completely unexplained. This is a major gap for usability.

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: formatting French phone numbers according to the ARCEP numbering plan, converting to E.164 and grouped formats. It also specifies the types of numbers handled (mobile, geo, voip, overseas) and explicitly excludes subscriber lookup, distinguishing it from potential alternatives.

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 usage when a French phone number needs formatting or validation, but it does not explicitly state when to use this tool versus others, nor does it provide alternative tool references. It mentions a cost and the ARCEP plan, which gives context, but lacks explicit when-not-to-use 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?

No behavioral traits are disclosed. The description does not mention side effects, permissions, data modification, or any other operational details. Since no annotations are provided, the description carries the full burden but fails to address this.

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 brief but includes an irrelevant and cryptic sentence about a payment ('Paid $0.01 USDC Base x402.'), which distracts from the core topic. It does not follow a clear structure and feels disjointed.

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 legal topic (prescription) is not explained in a way that helps an agent understand the tool's function or usage. The payment sentence adds noise instead of context, and no output or return behavior is described. Overall, the description leaves the tool severely under-specified.

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 no parameters, but the description does not clarify what input the tool expects (e.g., an invoice date or amount). The schema itself is an empty object with additionalProperties true, so there is nothing for the description to add, yet it also fails to provide any hint about usable parameters.

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 mentions 'French limitation period for an unpaid invoice' but lacks a clear verb indicating what the tool actually does (e.g., calculates, returns, checks). The added sentence about payment is unrelated and confusing, further muddying the purpose.

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 any alternative. The description provides no context for selecting this tool among the many siblings listed.

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 full responsibility for explaining behavior. It does not describe what the tool does, its effects, or any side conditions (e.g., whether it reads, writes, or updates). The mention of 'Paid $0.01 USDC Base x402' is cryptic and unexplained, offering no transparency about actual 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 extremely brief but poorly structured. It is a fragmentary set of phrases without logical flow or clear subject-verb-object construction. The inclusion of seemingly random elements ('Optional number', 'Paid $0.01 USDC Base x402') makes it disjointed and hard to parse.

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 severely incomplete. It does not explain the tool's role in the broader system, what inputs or outputs to expect, or any relevant context such as what 'CGI 289' refers to. Even the basic purpose is not fully clarified, leaving an agent without enough information to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so schema coverage is effectively 100%. According to the baseline rule, a score of 3 is appropriate even without additional parameter information. The description does not need to explain parameters because there are none.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it is a 'French pro forma header' and notes it is not an invoice (CGI 289), but it lacks a specific action verb or clear indication of what the tool does. The phrases 'Optional number' and 'Paid $0.01 USDC Base x402' add confusion rather than clarity, making the purpose ambiguous.

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 sibling list contains many related tools, but the description does not mention any conditions, dependencies, or reasons to choose this tool over others.

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 must carry the full behavioral burden. It explains the calculation formula (days / days in start month) and includes a cost note ('Paid $0.01 USDC Base x402'), which hints at a monetary side effect. However, it does not disclose whether the operation is read-only, what happens with invalid dates, rounding behavior, or any error conditions. The cost note is positive but incomplete.

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 with no fluff. The core purpose is front-loaded, and the cost note is secondary. It is concise and structured logically, though the pricing information could be separated 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?

For a tool with no output schema and no annotations, the description is too sparse. It does not specify the return value (the calculated prorated amount), the expected input format (e.g., date strings, numeric amount), or edge-case behavior. An agent would struggle to call this tool correctly without further information.

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 defines zero parameters (additionalProperties: true), so the description must compensate. It references 'monthly HT amount' and 'from/to window,' implying the expected inputs, but does not provide parameter names, types, or required flags. Baseline for 0 params is 4, but the description's ambiguity about exact argument structure lowers it to 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific calculation: 'Calendar prorata of a monthly HT amount over an inclusive from/to window.' It identifies the verb (prorata), resource (monthly HT amount), and window (inclusive from/to), but leaves inputs vague—no mention of how the amount or dates are provided. It distinguishes from siblings by being a calculation tool, though not explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. The sibling list includes related terms like 'jours_francs' (days) and 'ht_ttc' (tax conversions), but the description does not explain when prorata is appropriate or which sibling to choose instead. No when/when-not guidance is given.

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 must carry the full burden of behavioral disclosure. It mentions 'Format only' but does not explain side effects, permissions, or whether it is read-only. The cryptic line 'Paid $0.01 USDC Base x402' is ambiguous and could be interpreted as a cost or unrelated note, further reducing 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 brief but includes an extraneous and confusing sentence about a payment ($0.01 USDC) that does not relate to the tool's core function. This detracts from clarity and structure, though the main point is conveyed in the first two sentences.

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 provides an example and clarifies the formatting nature, but it lacks context on when this tool is needed, what the output should look like beyond the example, and the odd payment note adds confusion. It does not fully equip an agent to decide when to use this 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 tool has zero parameters, so schema coverage is 100%. The description does not add any parameter-specific information, but since there are none, 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 clearly states that the tool formats a French RCS invoice mention, provides a concrete example ('RCS Pau 404 833 048'), and explicitly notes it is 'Format only, not a Kbis lookup', which distinguishes its purpose effectively.

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 only usage hint is the negative clarification 'not a Kbis lookup', which implies it should not be used for lookups but does not explicitly state when to use this tool versus alternatives. No positive guidance or conditions are provided.

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 per-invocation cost ('Paid $0.01 USDC Base x402'), which is a significant behavioral side effect. It does not explicitly state whether the tool is read-only or mutating, but since it generates a clause, the likely read-only nature is implicit. The cost disclosure is a transparency plus.

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 exceptionally compact—two sentences—yet conveys the legal basis, the substantive effect, the scope exclusion, and the payment cost. Every word adds value and the structure is clean and direct.

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 no parameters and no output schema, the description gives enough context: it states what the clause is, when it applies, and what it costs. It does not explicitly describe the return format, but the nature of a clause generator makes the output obvious. Given the simplicity, the description is nearly 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 parameter schema is empty (only additionalProperties: true) and the description provides no information about what parameters, if any, are expected or accepted. Since schema coverage is effectively 0%, the description fails to compensate by explaining input requirements, leaving the caller without guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as generating a French retention-of-title clause under C. com. L.624-16, specifying that goods remain the seller's property until full payment. It also explicitly scopes the tool to goods and excludes pure services, leaving no ambiguity about its purpose.

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 an explicit exclusion ('Not for pure services'), which implies the tool is intended for sale-of-goods contexts. However, it does not name alternative tools or give a positive 'when to use' beyond that exclusion, so guidance is present but not fully 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?

There are no annotations, and the description provides minimal insight into side effects or costs. The phrase 'Paid $0.01 USDC Base x402' hints at a payment or fee but is unexplained, leaving the tool's behavior opaque.

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 packs several legal specifics into a short text. However, the inclusion of 'Paid $0.01 USDC Base x402' feels out of place and slightly disrupts the flow, though it does not significantly harm 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's purpose is fairly self-contained, but the description lacks any mention of what the tool returns or expects as input (beyond an empty schema). The payment reference is unexplained, leaving some context missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is empty, so there are no parameters to describe. With 100% schema coverage, the baseline is 3, and the description adds no further parameter information.

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 subject as French 14-day consumer withdrawal and provides key legal details (start dates for services and goods, exclusion of professional buyers). However, it lacks an explicit verb such as 'compute' or 'retrieve', making the tool's exact function slightly ambiguous.

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 states that it does not apply to professional buyers, which implicitly indicates a B2C context, but it does not explicitly say when to use this tool versus alternatives among the many sibling legal terms. Usage guidance is inferred rather than 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. It discloses the payment cost ($0.01 USDC Base x402) and mentions an optional controller name, but does not describe the return format or any side effects, which are important for a paid tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the core purpose, followed by essential cost information. Every sentence earns its place with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with no params and no output schema, the description covers purpose and cost but omits what the tool returns and how to pass the optional controller name. This leaves some ambiguity for the 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?

There are no defined parameters, but the description adds meaning by mentioning an optional controller name, which is not in the schema. This helps the agent understand a possible input even though the schema is empty.

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: generating a French invoice personal-data footer with RGPD legal bases and retention period. It is specific and distinguishes from siblings by focusing on GDPR compliance, though it doesn't explicitly say it returns the footer text.

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 on when to use this tool versus alternatives. It does not mention exclusions or compare to sibling tools like 'conservation' or 'prescription', leaving the agent to infer its specific use case.

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 burden of behavioral disclosure. 'Format only' is a useful signal that this is a formatting tool rather than a validation or lookup tool, but the description does not explain the output shape, how inputs are accepted (given the open additionalProperties schema), or any edge cases. The 'Paid $0.01 USDC Base x402' sentence is irrelevant noise that detracts from behavioral clarity.

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 core explanation is tight — purpose, format example, and RNE context in two sentences. However, the trailing 'Paid $0.01 USDC Base x402' is irrelevant to tool selection or invocation and should be removed. Slightly above minimum for structure but not exceptional.

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 format example ('RM Pau 404 833 048') and the RNE/RM context are genuinely helpful and cover the 'why/when' dimension. However, with no output schema and an open input schema, the description does not clarify how to supply the city + SIREN/SIRET inputs (property names) or what the exact output string looks like beyond the example. Missing input-handling details keep this from being 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?

There are zero structured parameters (baseline 4), and the description compensates by naming the expected inputs: 'city + SIREN/SIRET'. This adds meaning beyond the open schema, which otherwise provides no parameter definitions. The description does not specify the exact property names an agent should pass, but the concept of the inputs is conveyed.

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 purpose: generating the French artisan RM invoice mention formatted as 'RM Pau 404 833 048' from city + SIREN/SIRET. The verb (format/generate) is implied rather than explicit, and it implicitly distinguishes from siblings like rcs_mention by focusing on RM rather than RCS. Purpose is clear and specific enough for an agent to route correctly.

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 useful temporal context — 'RNE replaced RM for new filings in 2023; invoice usage still shows RM' — which tells an agent when RM is still applicable. However, it does not explicitly name alternatives (e.g., rcs_mention for RCS registrations) or state when NOT to use this tool. Usage guidance is present but implicit.

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 does disclose that it is 'Format only, not a Kbis', which clarifies a key behavioral trait. However, it does not describe what the tool returns (e.g., a static string or template), any side effects, or the meaning of the 'Paid $0.01 USDC Base x402' note, which is cryptic and potentially confusing.

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 mostly concise and front-loads the core purpose, but the appended 'Paid $0.01 USDC Base x402' is irrelevant to the tool's function and could mislead or distract an agent. This reduces clarity and structural efficiency.

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, the description is fairly complete in explaining what the mention contains and that it is format-only. However, it does not specify the exact output format (e.g., whether it returns a ready-to-use string or a template with placeholders), and the unrelated payment note adds noise. With no output schema and no annotations, a bit more detail on the return value would improve completeness.

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 schema coverage is trivially 100%. Per the calibration, a baseline of 4 is appropriate because there are no parameters to explain. The description does not need to add parameter semantics.

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: generating the French siège social invoice mention (L441-9) with specific components (street, postcode, city, department prefix, Alsace-Moselle flag). It explicitly distinguishes itself from a Kbis, which differentiates it from sibling tools like rcs_mention or rm_mention.

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 usage for French invoice legal mentions and explicitly says 'Format only, not a Kbis', which clarifies when not to use it (for Kbis). However, it does not provide explicit guidance on when to choose this over other mention tools like mention_fields or rcs_mention, leaving the selection to inference.

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

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

The description discloses the computational nature of the tool and its cost, and explicitly states that no INSEE lookup occurs. However, with no annotations, it does not fully clarify side effects or whether the tool is read-only, though the described behavior implies a pure computation.

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 packs in the key operations, the no-lookup caveat, and the cost. No unnecessary words or redundancy are present.

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?

While the description lists the operations, it lacks critical context such as the expected input format and the structure of the output. Since there is no output schema, the return format should have been described for the tool to be used 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 input schema is empty with additionalProperties true, and the description does not specify the parameter name, type, or format for the SIRET value. An agent has no way to know how to pass the input to this 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 clearly states the tool's specific operations: splitting a French SIRET into SIREN and NIC, checksumming both, and computing the VAT key. It also mentions 'No INSEE lookup', which helps differentiate it from potential external-lookup 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 provides some usage context by noting there is no INSEE lookup and that the tool costs $0.01, but it does not explicitly explain when to choose this tool over sibling tools like 'vat_key' or 'check_siret'. More direct selection guidance would improve this score.

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 key behavioral trait: using the tool requires a payment of $0.01 USDC Base x402. It also sets expectations about the non-authoritative nature of the data ('Not a tax ruling'). However, it does not specify whether the tool is read-only, whether the payment is a one-time fee or per-call, or what the exact return format looks like.

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 brief and to the point. Each sentence serves a purpose: listing the rates, clarifying the indicative nature, and flagging the payment. There is no redundant or filler content, making it highly efficient for an agent to parse.

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 provides core information about the data and the cost, but lacks some context. It does not specify the output format (e.g., a table, a JSON object), how the payment is processed or verified, or any special instructions for invoking the tool. Given the low complexity, these omissions prevent it from being 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 schema is an empty object with additionalProperties true, meaning any parameter could be passed but no parameters are formally defined. The description does not clarify what inputs (if any) the tool accepts, such as a product category or a year. This leaves the agent with no guidance on how to pass parameters or whether parameters are even allowed.

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 an indicative French VAT rate table with the exact rates listed (standard 20, intermediate 10, reduced 5.5, super_reduced 2.1, exempt). It unambiguously states what resource is being provided and distinguishes it from tax advice by saying 'Not a tax ruling.' This makes the purpose immediately clear.

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 explicit guidance on when to use this tool versus alternatives. While it notes the table is 'indicative' and 'Not a tax ruling,' it does not mention any sibling tools or conditions for selection. An agent would not know whether to pick this over related tools like 'vat_key' or 'ht_ttc' based on the description 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?

The description says 'Optional qty with plural' and 'Format only,' suggesting formatting behavior and a cost ('Paid $0.01 USDC Base x402'). However, with no annotations, it does not disclose side effects, authentication requirements, or failure modes, and the payment note is unexplained.

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 to the point, but it includes the cryptic 'Paid $0.01 USDC Base x402' which is not clearly relevant to the tool's function and may confuse rather than inform. Overall, it is compact but slightly cluttered.

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 parameters and no output schema, the description could still be complete, but it fails to clarify the tool's role among many similar siblings. The purpose is vague, and the payment/cost note introduces an unexplained dimension, leaving the agent without enough context to use it confidently.

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 coverage is complete and there is nothing to describe. The baseline of 4 applies because the description need not explain nonexistent inputs.

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 French invoice line unit of measure and lists allowed values, but it does not state what the tool actually does (e.g., validate, format, or suggest). The phrase 'Format only' hints at behavior but leaves the primary purpose ambiguous.

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 the many related siblings (e.g., tva_rate, vat_key, ht_ttc). There is no mention of prerequisites, input context, or typical scenarios, leaving the agent to guess.

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 burden of behavioral disclosure. It discloses the cost (paid $0.01), the computational formula, and the limitation (not a VIES proof). This goes beyond what structured fields would provide, but it omits how the SIREN input is supplied, which is a minor behavioral gap.

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, front-loading the purpose and formula in the first sentence, then adding disclaimers. Every sentence contributes meaningful information: purpose, formula, validation caveat, and cost. There is no 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?

While the description covers the formula, limitations, and cost, it does not clarify how the SIREN is provided given the empty input schema. The tool appears to rely on context or an implicit input, but this is not stated. Additionally, the output format is implied (the VAT identifier) but not explicitly described. These gaps reduce completeness for an agent deciding 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 tool has zero parameters, so the baseline is 4. The description doesn't need to explain parameters, and the schema is trivially covered. No additional parameter semantics are required.

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 function: it computes a French intra-community VAT identifier from a SIREN, provides the exact formula, and distinguishes it from a VIES validation tool. This is specific and unambiguous, and it differentiates from sibling tools like check_siret and siren_from_siret by its unique output and formula.

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 explicitly warns 'Not a VIES proof', which tells the agent when not to use it (for validation). It also mentions the cost, which is a practical usage consideration. However, it doesn't name specific alternative tools or provide detailed when-to-use vs. when-not-to-use guidance beyond the VIES exclusion.

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