Sirenic

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

With no annotations, the description discloses return format (base64), size range (1-10 MB), payment mechanism (x402, $0.10), and the quote flow. It lacks permissions or rate limits but covers key behaviors.

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

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

Two sentences, front-loaded with purpose, covering all essential aspects without redundancy.

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

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

The description explains input, output format/size, and payment details. It omits error handling and authentication beyond payment, but for a download tool it is quite 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?

Schema coverage is 100%, providing baseline 3. The description adds context by reinforcing the use of IDs from the list tool and explaining the 'type' parameter with examples, improving clarity.

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 verb (Download), resource (official company document PDF from INPI RNE registry), and provides examples of document types, distinguishing it from sibling tools like get_french_company_pdf_report.

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 tells the agent to use IDs from list_french_company_documents and mentions the payment cost, but does not explicitly compare to alternatives or state when not to use.

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?

Discloses key behaviors: deposits are immutable, format differs by date (post April 2022), payment required, reference source. No annotations provided, so description carries the full burden; it does well but could mention error responses or rate limits.

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

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

Two concise sentences that front-load the core purpose (retrieve deposit) and then provide specific details on format, source, immutability, and payment. No wasted 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?

Given no output schema, description hints at return structure (structured JSON for recent, PDF base64 for older). Covers source, payment, and immutability. Could elaborate on response fields or error conditions for full 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?

Schema coverage is 100%, so parameters are documented. The description adds value by tying reference to list_belgian_company_filings and explaining the x_payment parameter (x402 header). Also clarifies that id is the 10-digit Belgian enterprise number.

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 states it retrieves a single Belgian annual-account deposit with specific format details (JSON or PDF). Distinguishes from list_belgian_company_filings and other sibling tools by focus on one filing and payment requirement.

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

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

Explicitly says reference comes from list_belgian_company_filings, providing clear usage context. Also mentions payment via x402. Does not state when not to use or mention 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?

The description discloses payment via x402 ($0.01 USDC) and mentions the returned fields, but does not cover error handling, rate limits, or authentication beyond payment. With no annotations, it carries the burden but 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?

Single, well-structured sentence. Key information is front-loaded: purpose, scope, schema uniformity, and payment. No unnecessary 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?

Without an output schema, the description lists the fields returned (identity, legal form, status, etc.), which is sufficient. It also covers payment. Complete for a profile retrieval tool.

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

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

Schema coverage is 100%, but the description adds value by explaining the x_payment parameter's role (paid via x402) and the uniform JSON schema across countries. This goes beyond the schema's basic descriptions.

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

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

The description clearly states it provides a unified European company profile by country and register ID, specifying the common JSON schema fields. It distinguishes itself from siblings which are mostly French-specific tools.

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

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

The description implies usage for pan-European company profiles, but does not explicitly state when to use this tool over alternatives or when not to use it. The context of sibling tools being French-specific provides implicit 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 provided, so description carries full burden. It discloses that only new BODACC publications are detected (not field-level edits), returns empty list if none, and reverse-chronological order. Payment cost is stated. Missing rate limits or auth details but adequate for a paid data 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?

Three sentences: first sets the context and purpose, second clarifies scope, third explains empty result and payment. No redundancy, key information front-loaded.

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

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

The description explains the return format (list of announcements, reverse-chronological, empty if none) and payment mechanism. Without output schema, this is sufficient. It does not detail what each announcement contains, but tool's purpose is polling, so completeness is adequate.

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

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

Schema description coverage is 100%, so baseline 3. The description does not add significant parameter details beyond the schema. It confirms 'siren' and 'depuis' usage and explains 'x_payment' as optional payment header, which is already clear from 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 specifies the verb 'get new official BODACC announcements since a date', the resource 'French company', and distinguishes from field-level profile edits. It also mentions poll-mode surveillance, clearly differentiating from sibling tools like profile or financials.

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 monitoring changes (poll-mode) and mentions payment via x402. However, it does not explicitly state when to use this tool over alternatives like get_french_company_legal_alerts or list_french_company_documents.

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 fully carries the transparency burden. It details the score components (financial ratios, company age, BODACC override), the output items (score, band, components, confidence level), and the payment requirement. This is comprehensive for a decision-support 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 a single, well-structured paragraph of four sentences. Each sentence adds value: output, methodology, limitations, and payment. No extraneous 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?

Given no output schema, the description adequately explains the return values (score, band, components, confidence). It covers the input (SIREN) and payment details. Minor gaps: no mention of error handling for invalid SIREN or payment failures, but the description is sufficiently complete for agent decision-making.

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

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

Schema description coverage is 100%, so the schema already documents both parameters. The description adds context that siren is a French company identifier and explains the payment signature's purpose, but does not provide additional semantic depth beyond the schema.

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

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

The description clearly specifies the tool returns a default-risk score (0-100) for French companies, based on financial ratios and a BODACC override. It is distinct from sibling tools like get_french_company_financials or get_french_company_health_summary, which address different 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?

The description states it is 'Decision-support only — NOT a solvency opinion or credit rating,' providing clear usage boundaries. It also mentions the payment via x402. However, it does not explicitly state when to use this tool 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?

No annotations provided, but description discloses payment requirement ($0.01 USDC), data sources (INPI/Banque de France), and scope (latest 3 fiscal years). It does not fully detail response behavior or error states but covers key 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?

Two concise sentences: one for data content, one for payment. No redundant information, front-loaded with main 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?

Without an output schema, the description lists returned fields (revenue, EBITDA, net income, ratios, liasse fiscale) but lacks full structure. It adequately covers the tool's complexity and payment process.

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?

Both parameters are described in the schema with clear meaning: 'siren' is a 9-digit identifier, 'x_payment' is an optional signature or omitted for a quote. The description adds context about USDC payment amount, enriching the schema.

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

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

The description clearly states the tool retrieves annual financial data from French company filed accounts, including revenue, EBITDA, net income, ratios, and full tax-form line items. It distinguishes itself from sibling tools like profiles or health summaries by specifying financial data and tax forms.

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 mentions payment via x402, hinting at a prerequisite but does not explicitly state when to use this tool over siblings like 'get_french_company_profile'. It lacks direct guidance on excluded 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?

With no annotations, the description does well by disclosing key behaviors: AI-generated content, French language, official data only, 7-day cache, and $0.15 USDC payment via x402. It does not mention error handling or rate limits.

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

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

Single sentence, well-structured, front-loaded with the core purpose. Every piece of information earns its place.

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

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

Given two parameters and no output schema, the description provides sufficient context: what the summary contains, language, data source, cache, and pricing. Missing details on error responses or the exact output format are minor given the rich description.

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

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

Schema coverage is 100%, so baseline is 3. The description adds context about missing x_payment meaning payment quote, but the schema already describes parameters adequately.

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 returns an AI-generated business-health summary of a French company, listing specific components like strengths, warning signs, activity trend, and confidence level. This distinguishes it from sibling tools such as get_french_company_financials or get_french_company_profile.

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 explains caching duration and payment model but does not explicitly state when to use this tool versus the many similar tools. No guidance on prerequisites 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?

Without annotations, the description fully discloses billing details (price per company, discount, payment via x402) and the trouve=false behavior for non-diffusible companies. Does not mention rate limits or idempotency, but the cost and not-found handling are well covered.

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

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

Three sentences, all substantive. Front-loaded with 'Batch KYB' and key benefits. No redundancy or filler. Every sentence earns its place.

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

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

Given no output schema, the description explains the edge case of found=false and billing. It covers usage, cost, and batch constraints. Minor missing details on response format, but sufficient for agent decision.

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

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

Schema coverage is 100%, but the description adds value by explaining billing context for x_payment (omit for quote) and clarifying the trouve=false behavior for sirens. This goes beyond the schema's literal descriptions.

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

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

The description clearly states it's a batch KYB tool for 2 to 100 French companies, distinguishing from single-company siblings like get_french_company_kyb_file. The verb 'batch' and resource 'KYB' are specific.

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

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

The description provides usage context ('ideal for prospecting and compliance agents processing lists') and implicit alternatives (single vs batch). It lacks explicit when-not-to-use or alternative tool names, but the context is clear.

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

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

With no annotations, the description must disclose behavioral traits. It mentions payment (x402) and lists outputs, but does not state whether the operation is read-only, idempotent, or what happens on invalid input. It adds some value but lacks full 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?

Single, front-loaded sentence that efficiently summarizes the tool's purpose and contents. No wasted words; all information is relevant.

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, the description provides a thorough list of output components. It covers payment info and scope. Could mention prerequisites (e.g., valid SIREN) but is otherwise complete for a paid aggregator tool.

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

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

Schema coverage is 100% with descriptions for both parameters (siren and x_payment). The description adds context about the payment cost and that it's optional, but does not expand on format or usage beyond the schema. So it is adequate but not exceptional.

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 returns a complete KYB file for a French company, listing specific components (identity, officers, alerts, financials, sanctions, VAT). It distinguishes from sibling tools like get_french_company_profile or screen_sanctions_lists by being comprehensive.

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

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

The description implies use when a comprehensive KYB file is needed, contrasting with more specific siblings. However, it does not explicitly state when not to use or provide alternative tool names, leaving some guidance 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?

With no annotations, the description carries the full burden. It discloses the payment requirement ('Paid via x402 ($0.01 in USDC)') and data source (BODACC), which are key behavioral traits beyond the schema. It does not mention rate limits or idempotency, but the payment disclosure adds significant value.

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 (20 words) that is front-loaded and to the point. Every piece of information (legal alerts, BODACC, examples, payment) earns its place with no waste.

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, the description explains the content of the return (alerts types) and the payment mechanism. It is fairly complete for the complexity of a paid data retrieval tool, though it could optionally mention what the payment quote response looks like if x_payment is omitted.

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

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

Schema coverage is 100%: both parameters (siren, x_payment) are described. The description does not add meaning beyond the schema, e.g., it doesn't clarify the siren pattern or the payment flow. Baseline 3 is appropriate since schema already documents parameters well.

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 retrieves 'Legal alerts' from the official BODACC gazette and lists specific types (insolvency proceedings, deregistrations, business sales). This verb+resource+scope is distinct from sibling tools like get_french_company_profile or get_french_company_financials.

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 legal alerts from BODACC are needed, but it does not explicitly state when to use this tool vs. alternatives like get_french_company_profile. No exclusions or when-not-to-use guidance is provided. The sibling list is available, but no comparative context 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 provided, so description carries full burden. It discloses payment requirement, base64 return format, caching condition for health summary, and the payment quote flow. This is good behavioral context, though rate limits or processing delays are not 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?

Two sentences, no wasted words. Front-loaded with the main purpose and contents. Could be slightly more structured (e.g., bullet points for contents) but remains efficient and 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?

Given no output schema, the description adequately covers return format (base64 PDF), contents list, payment mechanism, and caching condition. It does not specify error handling for missing SIREN or file size limits, but overall it provides sufficient context for an AI agent to understand its 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?

Schema coverage is 100% with basic descriptions. The description adds value by explaining that x_payment is optional and that omitting it returns a payment quote. It also clarifies the purpose of the parameters within the overall workflow.

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?

Description clearly states the tool produces an on-demand PDF report of a French company, listing specific contents (identity, officers, legal alerts, financials, sanctions screening, AI health summary when cached). This distinctively separates it from sibling tools like get_french_company_profile or get_french_company_financials.

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?

Implies usage for obtaining a comprehensive KYB PDF report and mentions payment via x402. However, it does not explicitly state when to use this vs. siblings (e.g., get_french_company_kyb_file), nor does it provide when-not-to-use guidance. The hint about omitting x_payment to get a quote is useful but not a full guideline.

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. It discloses that the tool is paid (cost of $0.005 in USDC via x402), which is an important behavioral trait. However, it does not mention whether the tool is read-only, whether it has rate limits, or what the response size might be. The payment disclosure is useful, but other behavioral aspects are lacking.

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: two sentences, the first states the main purpose and lists data fields, the second notes the payment requirement. No redundant information.

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

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

The description covers the core purpose, key data, and payment model. However, with no output schema, it does not describe the return format (e.g., JSON structure, error handling). For a tool with two parameters and no nesting, this is mostly sufficient but could be improved by noting typical output.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds significant value by explaining the payment parameter (x_payment) and its usage, including that omitting it returns a payment quote. For the 'siren' parameter, it confirms the 9-digit pattern already in the schema.

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

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

The description clearly identifies the tool's purpose: retrieving the full official profile of a French company using a SIREN number. It lists specific data fields (legal name, legal form, etc.), which distinguishes it from sibling tools like get_french_company_financials or get_french_company_health_summary.

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 complete official profile is needed, but it does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention when not to use it. Among siblings, there are more specific tools for finance, health, or legal alerts, but no comparative guidance is offered.

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 mentions the x402 microtransaction payment, which is a key behavior. However, it does not reveal other aspects like data freshness, error handling, or authorization requirements.

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 long with no wasted words. It front-loads the core purpose and includes the payment detail efficiently.

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 output schema, the description adequately explains return data (contracts with buyers, amounts, dates) and the payment mechanism. It is missing a brief note on what omitting payment does, but the schema covers that.

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

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

The schema description coverage is 100%, setting a baseline of 3. The description reinforces that 'siren' is for the company and 'x_payment' for payment header, but adds little beyond the schema itself.

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 returns public procurement contracts won by a French company, with specific fields (buyers, amounts, dates). It distinguishes from sibling tools like 'get_french_company_profile' which returns general company info.

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 alternatives like 'get_french_company_financials'. No when-not-to-use or context 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 carries full burden. It states the tool returns 'deposit references with filing metadata as published' but does not disclose behavior such as pagination, rate limits, or what happens if no filings exist. The description provides some context but lacks full 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 two sentences, front-loads the main action, and every word is meaningful. No redundant 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?

Given no output schema, the description partially explains the output ('deposit references with filing metadata') but lacks details on the structure, pagination, or handling of edge cases. The payment model is mentioned, but completeness is average.

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

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

Schema description coverage is 100% for both parameters (id and x_payment). The description adds context about the output (references and metadata) and payment, but the schema already explains the parameters adequately. Therefore, the description adds marginal value beyond the schema.

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

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

The description clearly states the tool lists 'every published annual-account deposit of a Belgian company' and specifies the source (official NBB). It distinguishes itself from siblings by claiming uniqueness: 'no other service exposes Belgian filed accounts.'

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 mentions 'Paid via x402' and 'unique on x402', implying when to use (for Belgian filed accounts) and that payment is required. However, it does not explicitly contrast with sibling tools like 'get_belgian_company_filing' or mention 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?

No annotations are provided, so the description carries full burden. It discloses the payment mechanism via x402 and cost ($0.02 in USDC), and that omitting payment yields a quote. However, it does not mention pagination, ordering, or behavior on invalid SIREN.

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

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

The description is two sentences, front-loaded with the main purpose, and includes all essential information without unnecessary 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?

Given no output schema, the description explains that document IDs are returned to download PDFs. It is sufficient for an agent to understand the workflow (list then download), but lacks details on error handling or return fields beyond IDs.

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

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

Schema coverage is 100% (both parameters described in schema). The description adds value beyond schema by explaining the cost context for x_payment parameter, clarifying its purpose and why it is optional.

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

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

The description clearly states the tool lists official documents filed by a French company at the INPI RNE registry, including specific types (legal deeds, annual accounts) and mentions document IDs for download. This distinguishes it from sibling tool download_french_company_document, which downloads a specific PDF.

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: call this to list documents, then use download_french_company_document to download PDFs. It provides clear context but does not explicitly state when not to use or prerequisites beyond the required siren parameter.

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. The description only mentions cost ($0.003 via x402) but does not disclose data coverage, pagination, error behavior, or read-only nature. With no annotations, the description must carry this burden but fails.

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

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

The description is very short (two sentences) with no redundancy. It conveys essential info efficiently, though it could be slightly better structured (e.g., separating payment info).

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

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

Given the tool's complexity (paid, requires SIREN, no output schema), the description mentions addresses and status response but omits how the payment flow works (e.g., quote step). Missing information about output structure.

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

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

Schema coverage is 100% (both parameters described). The description adds no new meaning to parameters beyond what the schema already provides. 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 description clearly identifies the verb ('list'), resource ('establishments of a French company'), and scope ('all'). It differentiates from siblings by focusing on SIRET rather than other company data.

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

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

The description implies usage for listing establishments given a SIREN. Sibling names are distinct (e.g., financials, profile), so context helps. Could explicitly state when to omit x_payment for a quote, but overall clear.

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

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

No annotations exist, so the description must carry the full burden. It discloses the payment model, active company filtering, and registry size, but omits rate limits, authentication requirements, error handling, or behavior when no results are found.

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, immediately stating the purpose, supported by key details (registry size, payment cost). No redundancy or unnecessary 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?

Given 12 parameters and no output schema, the description covers the core functionality and cost model well. Minor gaps remain (e.g., parameter exclusivity, pagination details beyond page count, error cases), but overall it enables an agent to understand the tool's scope.

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

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

Schema coverage is 75% (9 of 12 parameters described). The description lists filter criteria broadly but does not compensate for the three missing parameter descriptions (age_max, effectif_max, effectif_min) in the schema, nor does it specify exclusivity between code_postal and departement.

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 a specific verb ('prospecting' with filtering) over a defined resource ('full French registry'), and distinguishes from sibling tools like search_french_companies or get_french_company_profile by emphasizing multi-criteria filtering and a per-page payment model.

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 explains the payment model and result size, implying usage for batch prospecting. However, it does not explicitly contrast with similar tools like search_french_companies, and lacks when-not-to-use guidance, leaving some ambiguity.

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 key behaviors: returns confidence scores not binary, and payment mechanism ($0.02 via x402). It doesn't cover rate limits or authentication, but the core behavior is well 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 three sentences, each serving a clear purpose: purpose, output format, payment. It is front-loaded and avoids unnecessary words, though it could be slightly more compact.

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?

Despite no output schema, the description explains the return type (fuzzy matches with confidence score). It covers the key behavioral and payment aspects. Missing details like no-match behavior, but overall sufficient for the complexity.

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

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

Schema coverage is 100% but the description adds value: explains that birth_year refines person matches, and that omitting x_payment yields a payment quote. This goes beyond the schema descriptions.

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

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

The description clearly states the action (screen), the target (5 official sanctions lists), and the output (fuzzy matches with 0-100 confidence). This distinguishes it from sibling tools which focus on company data rather than sanctions screening.

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 sanctions screening) and explicitly names the lists used. However, it doesn't mention when not to use it or suggest alternative tools, though the context from siblings makes the differentiation clear.

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

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

No annotations are provided, so the description carries full burden. It discloses the payment mechanism (x402, $0.003) and unified schema but omits details like pagination, error handling, case sensitivity, or authorization 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 a single concise sentence that front-loads the core purpose and includes essential payment information. No wasted 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?

Given no output schema and no annotations, the description should cover return format and behavior. It mentions 'unified schema' but does not describe it, nor does it address result limits, pagination, or which registers are always available.

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

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

Schema coverage is 100% with parameter descriptions. The description adds context (payment, registers) but does not significantly enhance parameter meaning beyond what the schema already provides. 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 description clearly states the tool searches European companies by name across official registers, listing specific countries and worldwide GLEIF/LEI coverage. It distinguishes from sibling tools like search_french_companies which are limited to France.

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 (broad European search) but does not explicitly state when not to use or provide alternatives. It mentions Denmark/UK when enabled but lacks direct comparison to siblings.

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 behavioral traits. It mentions payment ($0.001 in USDC via x402) and returns top 10 matches. It does not cover what happens on no results, rate limits, or authentication beyond the optional x_payment parameter.

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

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

Two sentences, concise and front-loaded. Every sentence adds value: purpose, data source, result limit, payment cost. No wasted 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?

For a simple search tool with one required param and an optional payment param, the description covers key aspects: what, data source, limit, cost. No output schema, but the return is implied as matching companies. Could mention return format but not critical.

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

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

Schema coverage is 100%, so the description adds minimal value beyond the schema. It reiterates 'name or SIREN' for the q parameter, but the x_payment parameter description is basic. 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 description clearly states it searches French companies by name or SIREN using official INSEE/INPI data, distinguishing it from sibling tools like search_european_companies. It also mentions payment and result limit, providing a specific verb and 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?

The description implies usage for searching French companies by name or SIREN and mentions the payment requirement. However, it does not explicitly state when not to use it or provide alternatives, though siblings offer some 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?

Without annotations, the description carries the full burden. It discloses the data returned (company SIREN, name, role), person data limited to surname, first names, role, birth year, and warns about homonym issues and payment. It lacks details on pagination or error handling but is fairly transparent for a search 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 a single, dense sentence that front-loads the main action and adds critical details (limitations, payment) without extraneous words. Every phrase contributes meaning.

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, the description provides a reasonable sense of return fields (SIREN, name, role). It mentions payment and limitations. However, it omits details like pagination, total results count, or error states, which would be helpful for a complete understanding.

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

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

Schema coverage is 100% (both parameters have descriptions). The description adds value by explaining the overall reverse director search functionality and the payment context, enhancing understanding beyond the schema's minimal descriptions.

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

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

The description clearly states the verb 'list' and the specific resource 'French companies where a person of a given surname holds an office,' distinguishing it from sibling tools like search_french_companies. It also adds context for due diligence and network mapping.

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 indicates usage for due diligence and network mapping, and mentions limitations like homonyms not disambiguated and capped common names. It does not explicitly state when not to use or alternative tools, but the purpose is clear enough to infer appropriate 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, the description carries full burden. It discloses that the call is paid (via x402, $0.003 in USDC) and uses the VIES service. However, it does not describe whether the operation is read-only, what the response format is, or if there are rate limits. The cost detail adds value, but significant behavioral aspects are missing.

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, well-constructed sentence that conveys the core purpose and payment detail without any superfluous words. It is front-loaded with the action and immediately informs the agent of cost implications.

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 output schema and the tool's simplicity, the description provides the essential purpose and cost, but it does not explain the nature of the output (e.g., validation result, possible errors). A more complete description would clarify expected return values or behavior on failure.

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

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

Schema coverage is 100%, so the input schema already provides descriptions for both parameters. The description adds no extra parameter-specific meaning beyond what is in the schema, except relating the x_payment parameter to cost. 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 description clearly states the action (validate), the subject (EU intra-community VAT number), the authoritative source (official VIES service), and scope (all member states). It distinguishes from sibling tools which focus on French company data or sanctions, making the purpose unambiguous.

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

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

No explicit guidance on when to use versus alternatives. The payment mention implies a cost structure, but no 'when not to use' or comparison with siblings like screen_sanctions_lists is provided. Usage context is implied by the tool's specificity but not formally articulated.

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