eu-verify

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

Discloses skipping weekends and 11 French holidays, movable feast computation, deterministic execution, JSON output, and pricing. No annotations exist, so the description fully covers 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?

Concise yet information-dense with examples and details. Minor lack of structure but 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?

Covers key behaviors for a business day calculator. Lacks error handling details and explicit output format specification (only 'JSON'), but is largely complete given 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?

Adds meaning via examples matching schema parameters (start, add), but introduces a 'mode' parameter not present in the schema, causing inconsistency. Schema coverage is 0%, so description compensates partially but with a flaw.

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 adds or counts French business days, specifying the resource and actions with examples. It distinguishes from sibling tools by its unique functionality.

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

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

Provides explicit usage patterns via query string examples for adding or counting business days. Does not mention when not to use, 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?

No annotations provided, so description must disclose behavioral traits. It only mentions 'FREE' and lists products, but doesn't clarify if it's read-only, idempotent, or any side effects. Minimal behavioral info.

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, zero waste. Front-loaded with 'FREE'. Every word 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?

Output schema exists, so return values are covered. Description provides purpose and usage hint. Missing some behavioral context, but adequate for a simple catalog 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?

No parameters, schema coverage is 100%. Description doesn't need to add parameter info. Baseline for 0 params is 4.

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 lists every product with specific details (HTTP endpoint, price, summary). The verb 'lists' and resource 'every product' are specific. It distinguishes from sibling tools which are specific checks or lookups.

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 'Use it to discover capabilities before paying', indicating it's for initial exploration. No when-not-to-use mentioned, but context is clear enough.

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: live validation, SOAP-to-JSON transformation, 24-hour caching, and pricing. It also explains the return values (valid/invalid, name/address 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?

The description is four sentences with no wasted words. It is front-loaded with the core purpose and includes necessary details. Minor improvements could be made to tighten phrasing, but it remains 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?

Given no output schema, the description fully explains the return values, caching behavior, and pricing. For a tool with one parameter and no annotations, this is complete and covers all aspects an agent needs to use it correctly.

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

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

The input schema provides only the parameter name 'eori' with no description (0% coverage). The description compensates by specifying the format (2-letter country + up to 15 alphanumerics) and providing an example, adding essential meaning 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 validates EORI numbers via the European Commission service, and explicitly describes the query format and purpose (customs clearance). It is easily distinguishable from sibling validation tools like validate_vat_eu or validate_siret_fr.

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?

While the description provides a specific example and context (customs clearance), it does not explicitly state when not to use this tool or contrast with alternatives. However, the purpose is so specific that usage is clear without additional guidance.

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

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

With no annotations, the description fully discloses behavior: returns newest-first, includes specific fields, caching (1h), pricing, and source. It also notes legal entities only, which is a key behavioral constraint.

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 packed with useful information in a concise manner. It starts with purpose, then details parameters, behavior, and context. Every sentence serves a purpose with no redundancy.

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

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

Given no output schema, the description explains return values, query syntax, pricing, caching, and source. It covers all necessary details 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?

Despite 0% schema description coverage, the description adds meaning: explains siren is Luhn-validated, famille optional with default, limit range 1-20, and example query. This compensates for the 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 states the tool returns legal announcements from the French BODACC for one company by SIREN. It specifies required and optional parameters. Among sibling tools, none focus on insolvency announcements, so it is distinct.

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 query syntax, optional filters, and context like 'legal entities only (GDPR-safe)' and 'clean-record signal'. It does not explicitly state when not to use or alternatives, but usage context is well explained.

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 '1h cache' and pricing ($0.01 per call, x402), essential for AI agents. No annotations exist, so description carries full burden. Behavior is transparent for a read-only 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?

Concise yet informative: purpose, example, field list, cache, price. Each sentence adds value, but some restructuring (e.g., bulleting fields) 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?

With no output schema, description lists notice fields (publication_number, etc.) and mentions source/cache/pricing. Adequate for a search tool, though pagination/errors are missing.

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

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

Schema has no descriptions (0% coverage), but the description adds semantics via example: cpv as '8-digit CPV code', country as '3-letter buyer country', and all parameters' optionality. Compensates well for schema gaps.

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 fetches 'Fresh EU public procurement notices from TED' with specifics (source, daily updates). It distinguishes itself from sibling tools (validation, company lookup) by targeting procurement.

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 an example query and explains each parameter (cpv, country, days_back, limit) with defaults and optionality, giving clear usage guidance. Does not explicitly contrast with alternatives, but domain is distinct.

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 carries the burden of transparency. It details all steps (Luhn, SIRENE, VAT computation/VIES validation), explains the possible verdicts (ready/not_ready/check_vat_manually), mentions caching (1h), pricing ($0.02 USDC), and notes that VIES flakiness never blocks the answer. This provides a comprehensive behavioral overview.

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 well-structured and concise. It starts with the main purpose, then provides the query format, lists the steps, explains the return value, and adds cache and pricing details. Every sentence adds value 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?

Given the tool's complexity (multiple checks, conditional verdict, caching, pricing) and the absence of an output schema, the description is highly complete. It covers input format, processing steps, possible outputs, and operational details (cache, price, VIES flakiness handling). No additional information is needed 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 schema provides no description for the single parameter 'number' (0% coverage). The description compensates by showing example queries ('?siren=552032534 or ?siret=55203253400041') and implying the parameter accepts a SIREN or SIRET string. However, it does not explicitly define the format or constraints, which would improve clarity further.

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: 'One-call compliance check for the French e-invoicing reform'. It specifies the context (French reform from 2026) and the actions it performs (Luhn checksum, SIRENE registry check, VAT validation). This distinguishes it from sibling tools like validate_siret_fr or validate_vat_eu, which perform individual checks.

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 that this tool should be used when a comprehensive compliance check is needed for French e-invoicing. It provides the query format and indicates it combines multiple checks. However, it does not explicitly state when to avoid using it (e.g., if only a simple SIRET validation is needed) or mention alternatives from the sibling list.

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 data source, licensing, coverage, caching, pricing, behavior for unknown LEI, and contents of response. No annotations provided, so description carries full burden and does it thoroughly.

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?

Every sentence adds value: purpose, data source, query example, features, pricing, caching, error case. Front-loaded and no redundancy.

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

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

For a tool with 1 parameter and no output schema, description covers inputs, outputs (listed items), pricing, caching, licensing. Lacks explicit response format but sufficiently 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 'lei' is explained (LEI identifier) with example value. Adds meaning beyond schema (just 'string'). No format/length constraints, but example covers typical usage.

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?

Specific verb+resource ('Who owns whom, from the official GLEIF LEI graph') clearly distinguishes from sibling 'lookup_lei' which likely does basic LEI lookup.

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

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

Clear context: queries ownership and returns multiple lookups in one call, implying efficiency. No explicit when-not-to-use comparison with siblings, but usage is well implied.

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 carries the behavioral disclosure burden. It details that personal data is stripped (GDPR), 24h cache exists, and a per-call cost of $0.005 USDC. These traits go beyond the schema and are essential for agent decision-making.

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 slightly verbose but well-structured: first sentence states purpose and source, then lists parameters with examples, then return fields, then extras like cost and cache. Every sentence provides value, though it could be tightened without loss.

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 (multiple parameters, no output schema), the description covers input format, behavioral notes, return fields, and cost. It is sufficiently complete 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?

Schema coverage is 0%, so the description must compensate. It explains that 'q' can be a name or SIREN number, defines 'per_page' range (1-10), and lists additional undocumented parameters (page, code_postal, activite_principale, etat_administratif) with examples. This adds rich meaning beyond the sparse schema.

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

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

The description clearly identifies the tool as an official French company registry search using the INSEE Sirene API, specifies the query parameters (name or SIREN), and lists key features. It distinguishes itself from siblings like 'validate_siret_fr' and 'verify_supplier_fr' by its focus on company data lookup.

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

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

Provides explicit context on how to query (by name or SIREN), optional parameters like per_page, page, code_postal, etc., and notes GDPR stripping and caching. However, it does not explicitly state when not to use or compare to sibling tools for exclusion.

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 caching behavior (24h), pricing ($0.005 per call), and outlines returned fields. With no annotations, it carries the burden of transparency effectively, though details on rate limits or authentication are absent.

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

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

Description is information-dense but relatively concise. Front-loads the main purpose with examples. Slight room for structuring key facts more clearly.

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

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

No output schema, but description lists all returned fields. Covers caching, pricing, and example queries. Missing error handling or pagination details but adequate for a simple lookup tool.

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

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

Since schema coverage is 0%, the description thoroughly explains all four parameters (lei, name, country, limit) with usage examples and meaning. Adds significant value beyond the empty schema.

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

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

Clearly states the tool provides legal entity reference data from GLEIF LEI golden copy, with specific lookup and search capabilities. Distinguishes from sibling tools by focusing on global LEI data rather than country-specific company lookups.

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 examples for direct lookup and search, including parameters and expected results. Implicitly suggests use cases but does not explicitly contrast with sibling tools for 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?

No annotations provided, so description carries full burden. It discloses daily refresh frequency, return data (scored matches, entity type, programs, verdict), and pricing ($0.01 USDC per call). Does not explicitly state read-only nature, but 'screen' implies no side effects.

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

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

Single, dense paragraph of three sentences. Front-loaded with purpose, then optional details, then pricing. 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?

Despite no output schema and 0% schema coverage, description covers daily refresh, query format, return structure, verdict categories, and cost. Omits error handling but is sufficient for a straightforward screening 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%, but description compensates by detailing parameter usage: name required, threshold range 0.6-1.0, and list values (eu,ofac,un,uk,fr). Default values (0.85 and empty) are not mentioned but implied.

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 specific sanctions lists (EU, US OFAC SDN, UN, UK FCDO, French asset freezes), with daily refresh and returns scored matches. It distinguishes itself from sibling tools which cover business, legal, and financial lookups.

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 and optional parameters (threshold, lists). Does not explicitly state when not to use or alternatives, but given sibling tools are unrelated, the context is clear enough for selection.

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 fully discloses the verification process (syntax check, MX lookup, domain detection), return verdicts, caching (1h), 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?

Compact yet comprehensive; uses clear sentence fragments and bullet-like structure. Every sentence adds value (process, results, cache, price). 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?

For a single-parameter tool with no output schema, the description fully covers behavior, results, use case, caching, and pricing. Completeness is high.

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?

Only one parameter (email) with 0% schema description coverage. Description adds meaning via example query and clarifies it's an email address to validate, but lacks detailed constraints.

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 validates email via syntax check and MX lookup, with specific verbs like 'checks', 'detects', 'returns'. Distinct from sibling tools which cover different domains (e.g., business days, IBAN, 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?

Explicitly mentions use case 'for lead qualification and list hygiene', providing clear context. However, no explicit alternatives or when-not-to-use guidance.

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

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

No annotations provided, so description bears full burden. It reveals deterministic offline computation, 1-year cache, pricing ($0.001 USDC), and return fields (valid, country, bban, failure reason). 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?

Three sentences: first defines core purpose, second gives example format, third summarizes returns, offline nature, cache, and price. Every sentence adds value; 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?

With only one parameter and no output schema, the description covers usage, return fields, and even pricing. It provides complete guidance for an agent to invoke and interpret results.

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 has one parameter (iban) with no description (0% coverage). The description adds a query example and notes tolerance for spaces/dashes, greatly enhancing understanding 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 'Deterministic IBAN check before a SEPA/international transfer' and specifies the checks performed (format regex, per-country length, ISO checksum). It uniquely identifies the tool's role among sibling validation tools.

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

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

It explicitly says 'before a SEPA/international transfer', providing clear context. While it doesn't mention when not to use, the description is sufficient given sibling tools cover other validation types.

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 discloses behavioral traits: auto-detection of SIREN vs SIRET, application of INSEE Luhn rule and La Poste exception, pure offline computation, 1-year cache, and pricing ($0.001 per call). This exceeds what annotations might typically cover.

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

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

The description is relatively concise at 5 sentences, front-loading the purpose. However, it could be slightly more structured (e.g., bullet points) to improve scannability. Still, it earns its place with no redundancies.

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 return values: 'Returns valid, type, siren, nic and the rule applied.' It also covers caching, pricing, and offline nature. For a 1-parameter validation tool, this is comprehensive.

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

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

The input schema has 0% description coverage for the single required parameter 'number'. The description compensates fully by explaining the format: '?number=44306184100047' and toleration of spaces/dots/dashes. It also clarifies that the number can be a SIREN or SIRET, which the schema does not indicate.

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: 'Instant pre-validation of French company numbers before invoicing or costly Sirene API calls.' It specifies the verb (validate) and resource (French company numbers), and distinguishes it from siblings by focusing on SIREN/SIRET and the cost-saving context.

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

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

The description explicitly suggests when to use this tool: 'before invoicing or costly Sirene API calls.' It implies not to use a costly API when this offline validation suffices. However, it does not provide alternative tools or explicit when-not-to-use conditions, which keeps it from a perfect score.

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

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

Discloses real-time query, 24h cache, and pricing, but does not mention error handling, rate limits, or authentication. Without annotations, more detail would be beneficial.

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?

Concise single paragraph that efficiently conveys purpose, usage, return data, caching, and pricing with no redundancy.

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

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

Describes return fields, caching, and pricing, but lacks details on potential errors or edge cases. Overall sufficient 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?

Despite 0% schema coverage, the description explains both parameters (vat: number without prefix, country: member state code including EL/XI) and provides an example, fully compensating for the schema's lack of 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 tool validates intra-EU VAT numbers in real-time via the VIES API, with a concrete example. It distinguishes itself from sibling validation tools like validate_email or validate_iban.

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 context (intra-EU, VIES API) and example query format, but does not explicitly state when to use or when not to use this tool versus 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 multiple behavioral traits: it uses an official data source, is continuously updated, supports forward/reverse modes, caches results for 24h, and has a specific pricing model. However, it mentions optional parameters (type, citycode, lat, lon) that are not present in the input schema, creating inconsistency and potential confusion. No annotations were provided, so the description carries full burden.

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

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

The description is relatively concise considering the amount of information it covers. It front-loads the main purpose and data source, then lists modes, parameters, response fields, and auxiliary details (caching, pricing). Slight improvement could be made by separating forward and reverse clearly, but overall 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?

Given the tool's complexity (geocoding with forward/reverse, optional filters), the description covers many aspects (response fields, error handling, caching, pricing). However, the mismatch between the parameters described and those in the input schema is a significant gap. Without output schema, the response information is useful but incomplete. The description would be more complete if parameters matched the schema.

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% (no descriptions in schema). The description adds meaning to the 'q' parameter by showing usage examples for forward geocoding and explaining the 'limit' parameter with a default and range. However, it also describes parameters not in the schema (type, citycode, lat, lon), which may mislead the agent. The description partially compensates for the lack of schema descriptions but with contradictions.

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. It distinguishes itself from sibling tools, which are unrelated (e.g., company lookup, sanctions screening). The verb 'verify' is somewhat ambiguous but the description clarifies geocoding.

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 using the tool (forward and reverse geocoding) and mentions optional filters. However, it does not explicitly state when to use this tool over alternatives or when not to use it. Since siblings are unrelated, the context 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?

No annotations provided, but description discloses graceful degradation on sub-checks, no charge on failure, pricing ($0.05 USDC), and output format (risk verdict with score and reasons). This adds significant behavioral context beyond schema.

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?

Description is a single paragraph but packs key information: purpose, inputs, checks, output, pricing, failure behavior. Could benefit from bullet points or better structure, but is concise and 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 no output schema, description adequately explains output (risk verdict with reasons and 0-100 score). Covers inputs, pricing, graceful failure, and all component checks. Complete for a single-parameter tool with this complexity.

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

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

Schema only has a 'number' parameter with no description (0% coverage). Description clarifies that it accepts SIREN (9 digits) or SIRET (14 digits) via 'siren=NNNNNNNNN or siret=NNNNNNNNNNNNNN', adding crucial semantics. Could specify exact format requirements like digits only.

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 performs comprehensive due diligence on French companies using SIREN/SIRET, listing specific checks (SIRENE, BODACC, VIES, sanctions) and outputs a risk verdict. It distinguishes from sibling tools like validate_siret_fr or check_insolvency_fr which are individual checks.

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?

Description positions the tool as a 'one-call due diligence' composite, implying it should be used when a comprehensive check is needed rather than individual checks. However, it does not explicitly state when to avoid using it or name alternatives.

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