eu-verify

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

The description fully discloses behavioral traits: skips weekends and French holidays (including movable feasts via Butcher-Meeus), deterministic local computation, JSON output, and cost per call. No annotations exist, so the description carries the full burden and meets it excellently.

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 front-loaded purpose and examples. It efficiently packs multiple details (holidays, modes, pricing) but could better separate parameter details from behavioral notes.

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 use cases (addition and counting), holiday handling, and pricing. However, it lacks explicit return value structure (though 'JSON' is mentioned), and the parameter schema mismatch leaves the interface incomplete for an agent.

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

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

The schema has 0% parameter description coverage, so the description must compensate. It explains 'start' and 'add', but introduces additional parameters ('from', 'to', 'mode') not present in the schema, creating confusion about the tool's actual interface. This mismatch undermines the agent's ability to correctly invoke the 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 adds French business days to a date or counts them over a range, with specific examples. This distinguishes it from sibling tools which are validation/lookup utilities.

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

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

Usage context is implied (French business days), but no explicit when-to-use or when-not-to-use guidance is given, nor are alternatives named. The description focuses on how the tool works rather than when to choose 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, so description carries full burden. It declares FREE and describes a read operation, but could mention limitations like pagination 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?

The description is extremely concise, front-loading 'FREE' and stating the purpose in two sentences with zero 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 parameters and an output schema, the description is mostly complete. It explains purpose and returned data, though authentication context is missing but implied by 'FREE'.

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?

No parameters exist, so schema coverage is 100%. The description appropriately omits parameter details since none 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 clearly states the tool lists every product (verb+resource) and specifies the information included (endpoint, price, summary). It distinguishes from siblings which are specific business operations.

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 advises using it to discover capabilities before paying, providing clear context. However, it does not explicitly mention when not to use or reference 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, so description carries full burden. Discloses live SOAP source, 24h cache, pricing ($0.003 per call), and that name/address returned only with consent. No contradictions.

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?

Packed with useful info but slightly verbose (e.g., 'clean JSON out' could be implicit). Front-loaded with main purpose. Could trim without losing 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 simple input (1 param, no output schema), description covers input format, output fields (valid boolean, name, address conditionally), caching, and pricing. Adequately complete.

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

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

Single parameter 'eori' with no schema description (0% coverage). Description adds format rule (2-letter country + up to 15 alphanumerics) and example, which compensates for schema gap.

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

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

Clearly states it performs live EORI validation via the European Commission service. Examples and return values are provided. Distinguishes from sibling tools (e.g., validate_vat_eu) by specifying the identifier type.

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 context: EORI needed for EU customs clearance. Includes query format example. Does not explicitly state when not to use or list alternatives, but context is sufficient for selection among 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 covers key behaviors: returns newest-first announcements with specific fields, only legal entities (GDPR-safe), caching for 1 hour, pricing per call. Does not mention rate limits or authentication, but the open data source implies public access.

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, then details query format, output, and metadata. However, it is a single dense paragraph; slight restructuring could improve scannability.

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 return fields, source, caching, and pricing. Covers all three parameters and provides usage context. No gaps for a simple query 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 0%, so description must compensate. It explains siren as Luhn-validated with an example, famille as optional filter for insolvency proceedings, and limit range (1-20) with default hint. Adds value beyond schema but could define other famille values.

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 retrieves legal announcements from the French BODACC gazette for a company using a SIREN number. It explicitly mentions 'insolvency proceedings' and distinguishes from sibling tools like lookup_company_fr which provide different 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?

Provides explicit query format with required and optional parameters, including the famille filter for insolvency. Mentions that zero announcements for a valid SIREN is a clean-record signal. However, it does not explicitly state when not to use this tool versus 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?

Without annotations, the description discloses important behavioral traits: data source (TED API), caching (1h), and pricing ($0.01 per call). It conveys it is a read operation with no destructive potential, though it does not mention authentication, rate limits, or empty result handling.

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 paragraph with no unnecessary words. It starts with the tool's purpose, then provides a concrete query example, lists returned fields, and ends with caching and pricing. Every sentence adds value and is efficiently 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?

Given four simple parameters, no output schema, and no annotations, the description is nearly complete: it explains the data source, parameter meanings via example, returned fields, caching, and pricing. Missing elements like pagination or error handling are acceptable for a straightforward 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 parameter descriptions are missing (0% coverage), but the description compensates well by explaining cpv as '8-digit CPV code', country as '3-letter buyer country', and showing an example that illustrates days_back and limit usage. It covers all four parameters indirectly, though units for days_back and limit constraints are implicit.

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 finds EU public procurement notices from Tenders Electronic Daily (TED). It specifies the source, recency ('new notices daily'), and provides an example query. No sibling tool covers tenders, so differentiation is inherent.

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 context (EU public tenders) and gives a query example with optional parameters. It does not explicitly state when not to use or compare to alternatives, but the sibling tools are all different domains (validations, company lookups), making the intended use 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?

Even without annotations, the description fully discloses behavior: runs multiple validations, caches results for 1h, handles VIES flakiness gracefully by returning 'check_vat_manually', and states pricing. This level of detail exceeds what annotations would typically provide.

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 (four sentences), front-loaded with the core purpose, and includes essential details (validations, caching, pricing) 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?

For a tool with one parameter and no output schema, the description completely covers input format, processing steps, possible output values, caching behavior, and pricing. No gaps remain.

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 provides only a string parameter 'number' with no description. The description adds crucial semantics by explaining it accepts SIREN or SIRET, giving examples, thus fully compensating for the 0% schema coverage.

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

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

The description clearly states it performs a one-call compliance check for the French e-invoicing reform, specifying the unique combination of checks (Luhn, SIRENE, VAT, VIES). This distinguishes it from sibling tools like validate_siret_fr or validate_vat_eu.

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

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

The description provides clear context for when to use the tool (French e-invoicing reform from 2026-09-01) but does not explicitly state when not to use it or mention alternatives. The specificity is sufficient for an agent to select it appropriately.

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 transparency is high: it discloses caching (24h), pricing ($0.005), and behavior on unknown LEI (returns found=false). It also mentions data source license and that it is a CC0 dataset. These are important behavioral traits that help the agent understand side effects and costs.

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, fitting in a few sentences with no redundant words. It front-loads the purpose with 'Who owns whom' and immediately provides source and coverage. Every sentence adds value (example, results, caching, pricing). It could be slightly more structured but 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 one-parameter tool with no output schema, the description covers the key aspects: what data is returned (four lookups), edge case (unknown LEI), caching, and pricing. It does not describe the structure of the response but given the lack of output schema, this is acceptable.

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

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

The input schema provides no description for the 'lei' parameter (0% coverage). The description compensates by explaining that the parameter is an LEI code and gives an explicit example. It does not provide detailed constraints (e.g., length, format) but the example is informative and sufficient for an 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 retrieves ownership relationships from the GLEIF LEI graph, listing specific data returned (entity name, status, direct/ultimate parent, children count/sample). It uses a concrete example query and mentions CC0 license and coverage. This differentiates it from the sibling 'lookup_lei' which likely only provides basic entity 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 implies usage for ownership queries but does not provide explicit guidance on when to use this tool versus alternatives like 'lookup_lei'. It does not mention prerequisites or when not to use it. Therefore, usage guidelines are implied 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?

Even without annotations, the description discloses key behaviors: it is a read-only search, returns company details, strips personal data (GDPR compliance), uses a 24h cache, and specifies a per-call price. This goes beyond what annotations typically provide.

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, packing much information into two sentences. It is front-loaded with the purpose and source. However, it is dense and could benefit from bullet points or clearer separation of query parameters and return fields.

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 complexity (multiple query parameters, no output schema, no annotations), the description is remarkably complete. It details the API source, query format, optional filters, return fields (SIREN, legal form, NAF, etc.), data privacy, caching, and pricing. No critical information is missing for an agent 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 JSON schema has no parameter descriptions (0% coverage), but the description significantly compensates by explaining the 'q' parameter (name or SIREN), defaults for 'per_page', and additional optional parameters like page, code_postal, activite_principale, and etat_administratif, even though these are not in the schema. This adds substantial meaning beyond the bare schema.

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

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

The description clearly identifies the tool as an official French company registry search via a specific API (recherche-entreprises.api.gouv.fr), with concrete query examples and details on data source and update frequency. It distinguishes itself from sibling tools like validate_siret_fr and lookup_lei by focusing on broad company lookup in 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 provides example queries and optional parameters, implying usage for searching companies by name or SIREN. However, it does not explicitly state when to use this tool versus alternatives like validate_siret_fr (for validation) or lookup_lei (for legal entity identifiers), nor does it mention prerequisites or exclusions.

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

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

Without annotations, the description covers key behavioral traits: daily updates, CC0 license, 24h cache, per-call pricing. It also lists output fields. While it does not mention rate limits or authentication, the transparency is strong for a read-only lookup 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 efficient paragraph that front-loads the core purpose and separates key details (lookup/search examples, output fields, caching, pricing). Every sentence adds value with 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 covers the tool's purpose, usage, output structure, caching, and pricing. It is largely complete, though could mention error handling or required authorization. Overall, it provides sufficient context 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?

With 0% schema description coverage, the description adds substantial meaning by demonstrating usage with examples (e.g., lei=... for direct lookup, name=airbus&country=FR&limit=5 for search). A minor inconsistency: the example uses limit=5 while schema default is 3, but this does not detract from overall 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 tool provides legal entity reference data from the GLEIF LEI golden copy, with distinct lookup and search modes. It differentiates from sibling tools (e.g., lookup_company_fr, lei_ownership) by focusing on LEI data and providing specific usage examples.

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 explicit examples for direct lookup and search, explaining when to use each parameter (lei vs. name+country+limit). It does not explicitly exclude alternative tools, but the context is clear enough to infer appropriate 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?

With no annotations, the description discloses key behavioral traits: daily snapshot refresh, threshold range, list options, return verdicts, and per-call pricing. It does not cover rate limits or error handling, but is sufficient for basic usage.

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 dense sentences: purpose, query format with parameters, return values. No redundancy, front-loaded with essential information. 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?

The description covers core functionality but omits details like the response structure (e.g., per-list dates, score format) and error cases. Given no output schema, a bit more on return format 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?

Schema coverage is 0%, so the description fully explains all three parameters: name (required), lists (default empty, values shown), threshold (default 0.85, range 0.6-1.0). It adds meaning beyond the schema's property titles.

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 screens a name against five official sanctions lists, with daily refresh. It specifies verb 'screen', resource 'name against sanctions lists', and distinguishes from siblings as the sole sanctions screening 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 provides explicit query parameters and pricing, making usage context clear. It does not offer explicit when-not-to-use guidance, but among siblings there is no alternative sanctions tool, so differentiation is unnecessary.

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?

Given no annotations, the description fully discloses behavioral traits: syntax check, live MX lookup over DNS-over-HTTPS with Cloudflare/Google fallback, caching (1h), verdicts (deliverable/risky/undeliverable), and pricing ($0.005/call). Nothing contradictory.

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, front-loaded with purpose, and every sentence adds value (syntax check, MX lookup, verdict, caching, pricing). 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?

The description is complete for this single-parameter tool: it explains input format, technical method, output verdicts, caching, and pricing. No output schema needed as return values are clearly described.

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 0% but the description adds meaning with an example ('?email=someone@example.com') and implies the parameter is an email string. It could explicitly state formatting requirements but provides sufficient 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 the tool is for email verification with specific checks: RFC 5322 syntax, MX lookup, NXDOMAIN detection, and null-MX detection. It distinguishes from sibling tools like validate_iban and validate_siret_fr by focusing on email deliverability.

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 explicitly mentions use cases: 'lead qualification and list hygiene'. However, it lacks explicit guidance on when not to use it or comparisons with similar validation tools among 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?

No annotations are provided, but the description fully discloses behavior: deterministic, offline computation, 1-year cache, pricing, input tolerance (spaces/dashes), and output fields (valid, country, bban, failure reason).

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 paragraph that efficiently conveys all key points. Minor improvement could be achieved with bullet points or clearer separation, but it remains clear and 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 the simplicity of the tool (one parameter, no output schema, no annotations), the description is fully complete: it covers purpose, input, output, behavior, and pricing, leaving no ambiguity for an AI 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?

With 0% schema description coverage, the description compensates by explaining the 'iban' parameter format with an example, tolerances, and its role in validation. This adds significant meaning beyond the bare string type.

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 validates IBANs deterministically for SEPA/international transfers, specifying the three checks (format regex, country length, checksum). It is distinct from sibling tools which focus on other validation domains.

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 use 'before a SEPA/international transfer', providing a clear context. It does not explicitly exclude alternatives, but no sibling IBAN tools exist, so the guidance is sufficient.

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 fully handles behavioral disclosure. It explains the tool is a pure offline computation with a 1-year cache, applies known rules (Luhn, La Poste exception), and returns specific fields (valid, type, siren, nic, rule). No destructive behavior is mentioned, and the pricing is transparent. The description adds value beyond what annotations would provide.

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 (three sentences) and front-loaded with the core purpose. Every sentence adds essential information: purpose, input format, rules, output, pricing. There is zero redundancy or fluff, making it highly efficient for an AI agent 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 tool's simplicity (1 parameter, no output schema), the description is complete. It covers the tool's purpose, input format with tolerance, validation rules, output fields, caching behavior, and pricing. No additional details are needed for an agent to understand and invoke 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 single parameter 'number' has no description in the input schema (0% coverage). The tool description compensates by detailing format tolerance (spaces/dots/dashes accepted), providing an example ('?number=44306184100047'), and explaining auto-detection of SIREN vs SIRET. This adds meaningful context beyond the plain schema definition.

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: pre-validation of French company numbers before invoicing or costly Sirene API calls. It distinguishes itself by auto-detecting SIREN vs SIRET and applying specific rules (INSEE Luhn, La Poste exception). The verb 'validate' and resource 'French company numbers' are specific, and it differentiates from siblings like validate_vat_eu which validate other entities.

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

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

The description provides clear context for when to use the tool: 'before invoicing or costly Sirene API calls'. It highlights its cheap offline nature with caching. However, it does not explicitly list alternative tools for other validation needs or state when not to use it, though the context implies it's for French SIRET/SIREN only.

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 fully discloses behavior: real-time query, 24h cache, price ($0.005 per call), return fields (is_valid, request_date, user_error). No contradictions.

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 (121 words) and front-loaded with purpose. Every sentence adds value: source, example, returns, cache, pricing. 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?

Given no output schema, the description adequately covers return values. Complexity is low. All necessary information for an AI agent to use the tool is present: parameters, behavior, pricing, and 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?

Schema coverage is 0%, but the description adds meaning by showing query format (?cc=IE&vat=6388047V) and explaining that 'vat' is number without country prefix and 'country' is member state code. This compensates for lack of 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 identifies the tool's function: 'Live intra-EU VAT number validation via the European Commission VIES REST API'. It provides a specific example and distinguishes from sibling validation tools (e.g., validate_email, validate_iban) by focusing on VAT.

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 VAT validation but lacks explicit guidance on when not to use or comparisons with siblings. However, the sibling set is diverse, so the purpose is self-explanatory.

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?

Given no annotations, the description fully discloses behavior: both forward/reverse modes, optional parameters, output fields, error response (400), caching (24h), and pricing. No contradictions.

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?

Dense but efficient, front-loaded with main purpose. Minor unnecessary detail about optional parameters not in schema 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?

Covers input, output, error handling, caching, and pricing. Missing output schema, but description compensates with detailed return fields. The schema-parameter mismatch detracts from 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?

Adds meaning to schema parameters (q as address query, limit as result count), but describes additional optional parameters (type, citycode, lat, lon) not present in the input schema, causing potential confusion for tool 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 the tool performs French address geocoding using the official Base Adresse Nationale, distinguishing it from sibling tools like company lookups or email validation.

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 clear usage instructions for forward and reverse geocoding, query parameters, limits, caching, and pricing. However, lacks explicit guidance on when to use versus alternatives or scenarios to avoid.

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 fully discloses behavior: sub-checks degrade gracefully, no charge on failure, output includes risk verdict with score and reasons, and price. This covers error handling and expected results.

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-loading the purpose and key details. It packs substantial information efficiently, though the first sentence is long and could be slightly restructured for readability.

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

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

Given one required parameter and no output schema/annotations, the description covers input format, checks performed, output structure, error handling, and pricing. It is fully self-contained 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?

The schema has no description for the 'number' parameter (0% coverage), but the description adds meaning by specifying the format 'siren=NNNNNNNNN or siret=NNNNNNNNNNNNNN', which is essential for correct 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 the tool's purpose as a comprehensive due diligence tool for French companies using SIREN or SIRET, listing specific checks (checksum, existence, insolvency, VAT, sanctions). It distinguishes from sibling tools by being a one-call composite, not a single check.

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 company due diligence and provides input format and pricing. However, it does not explicitly state when to use alternatives from the sibling list or when not to use this tool.

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