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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, and the description adds a non-obvious behavioral detail: label resolution automatically falls back across all 24 official EU languages. This extra transparency is useful and does not contradict any annotations. No side effects or rate limits are mentioned, but none are expected for a read-only search.

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 that is concise yet informative. It front-loads the core purpose, then adds a use case, an example, and a key behavior. No redundant or filler content is present.

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

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

The description provides enough context for a user to call the tool correctly. It mentions the concept input, language fallback, and the fact that it searches by EuroVoc. Since the context signals indicate an output schema exists, the description is not required to detail return values. The description is complete for the tool's intended use.

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

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

The schema covers all parameters (concept, language, resource_type, limit) with descriptions. The description adds clarifying examples ('artificial intelligence', a EuroVoc URI) and explains the language fallback behavior for the `language` parameter. This goes beyond the schema's basic descriptions, providing practical guidance on how to construct valid queries.

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

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

The description clearly states the tool's function: 'Searches EU legal acts by EuroVoc thematic concept'. It also gives a specific use case ('documents about X' when the term may not appear in the title) and provides a concrete example ('artificial intelligence'). This distinguishes it from sibling search tools and leaves no ambiguity about its purpose.

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

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

The description explicitly identifies the tool as 'the right tool for "documents about X" when the term may not appear in the title', giving a clear condition for use. It also explains the language fallback behavior, which helps the user understand how to supply the concept. It does not explicitly mention alternatives or when not to use it, but the guidance is sufficient 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?

The annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral context such as how query matching works (contiguous phrase, case-insensitive, boilerplate prefix) and that rulings without a title in the selected language yield no result. This goes beyond the annotations.

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

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

The description is well-structured, with the main purpose first and parameter-specific guidance following. Every sentence adds value, with examples and clarifications that are useful without being verbose.

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

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

Given the output schema exists and is rich, the description does not need to explain return values. It provides comprehensive guidance on all parameters, explains edge cases (language availability, query prefix behavior), and differentiates from sibling tools, making it complete for the tool's 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% and the description adds significant semantic detail beyond the schema, including clear examples for ecli, celex_id, related_celex, explains the query matching behavior and the meaning of type/court enums, and notes the language limitation. The description adds value beyond the already thorough 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 finds CJEU case law and explicitly distinguishes it from eurlex_search which searches legislation. It specifies the resource (CJEU case law) and the action (finds), and differentiates from siblings.

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 guidance on when to use this tool versus alternatives, stating 'Unlike eurlex_search (which searches legislation by title), this tool is scoped to case law and understands ECLIs and act-to-case-law relations.' This clearly signals the appropriate 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?

Beyond the annotations (readOnlyHint, idempotentHint), the description reveals additional behavioral nuances: the balanced split ensures recent cited_by entries do not crowd out cites, the response includes a counts field, and the limit is not back-filled. These details are not present in the annotations and help set expectations for the response shape and edge cases.

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 main purpose, then elaborates on the direction behavior. However, there is some redundancy: the balanced split and counts field are described, then repeated with alternative wording about the limit division. This repetition adds a bit of bloat but does not obscure 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?

The description covers the tool's core behavior, including defaults, edge cases (fewer results when balanced), and a key response field (counts). The context signals indicate an output schema is available, which would supply the full response structure. Overall, the description is sufficient to call the tool correctly without missing critical information.

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

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

Schema coverage is 100% and each parameter has a descriptive entry, including enum values and defaults. The description adds a little extra context for the 'direction' parameter (e.g., explaining the balanced split in more narrative form), but it largely echoes the parameter descriptions. Since the schema already carries the semantic weight, the additional description provides only marginal value.

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

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

The description clearly states the verb ('Finds') and the resource ('citation relationships for an EU legal act'), distinguishing it from sibling tools like eurlex_search or eurlex_metadata. It also specifies the key directional options and the balanced split behavior, making the tool's 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?

The description provides strong contextual cues about when to use the tool (e.g., when citation relationships are needed) and explains the behavior of the 'direction' parameter, including the balanced split and potential reduction in results. It does not explicitly name alternative tools or exclusion criteria, but the detail is sufficient for a typical caller to decide when to invoke 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?

Annotations already indicate readOnlyHint, idempotentHint, and destructiveHint=false, establishing safety. The description adds that it merges amendments, which is a behavioral detail. It does not mention pagination or error behavior, but those are not required given the strong annotation coverage. No contradictions with annotations are present.

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 concise sentences with no filler. It front-loads the main action, then explains identification requirements and the CELEX pattern. Every sentence contributes useful information 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 (8 parameters, two mutually exclusive input forms), the description covers the essential usage constraints and the output context is handled by the existing output schema. It does not need to explain return values because an output schema is present. The description is complete for an agent to correctly invoke the tool.

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

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

Schema descriptions cover 100% of parameters, including enums and patterns. The description adds the key constraint that celex_id and doc_type+year+number are mutually exclusive ('provide exactly one of the two') and clarifies the CELEX format as '3YYYY[R|L|D]NNNN,' which goes beyond the schema pattern. This enhances the parameter semantics.

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

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

The description clearly states it 'Fetches the latest consolidated (currently in-force) version of an EU legal act via ELI, with all amendments merged in.' It uses a specific verb and resource, and the title 'Get consolidated EU legal act' reinforces the purpose. It is distinguishable from siblings like eurlex_fetch or eurlex_metadata, which focus on other 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 gives concrete usage guidance by specifying the two identification forms (celex_id or doc_type+year+number) and the requirement to 'provide exactly one of the two.' It also explains the CELEX pattern. However, it does not explicitly contrast with sibling tools (e.g., when to use this vs. eurlex_fetch for non-consolidated versions), which would make the guidance more 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?

The description is consistent with the readOnlyHint, idempotentHint, and destructiveHint annotations, but it does not add any behavioral context beyond those annotations (e.g., no side effects, no rate limits, no error behavior). Since annotations already cover the safety profile, this is adequate but not enhanced.

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, tightly packed with essential operational details (identifier selection, pagination) and contains no extraneous 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 the detailed output schema and high parameter coverage, the description provides sufficient context for invocation: identifier selection, pagination, and format choice. 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?

Schema descriptions cover 100% of parameters, so baseline is 3. The description adds extra clarity on pagination semantics (pass previous next_offset) and the mutual exclusivity of identifier parameters, which exceeds the schema-only information.

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

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

The description clearly states the tool fetches the full text of an EU legal act, and identifies the three mutually exclusive identifier options (celex_id, eli, oj_ref). This is specific and unambiguous.

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

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

The description provides explicit guidance on pagination (using offset and max_chars, passing next_offset) and insists on providing exactly one identifier. However, it does not explicitly compare against sibling tools (e.g., eurlex_summary, eurlex_metadata) to indicate when this tool is preferred.

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 is transparent about the resolution behavior ('Resolved to a CELEX ID via Cellar') and it is consistent with the readOnlyHint, idempotentHint, and destructiveHint annotations. It does not hide side effects or claim mutating behavior.

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

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

The description is well organized and informative, but it repeats 'Provide exactly one of celex_id, eli, or oj_ref' in each identifier parameter description. This is a minor redundancy rather than a structural problem.

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 output schema is available, the description does not need to enumerate return fields. It covers all invocation inputs, gives realistic examples, and states the language default, making it sufficient for an agent to call 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 input schema already covers all four parameters, and the description adds valuable meaning: concrete examples for each identifier type, the exact-one-of constraint, and clarification that language controls title and EuroVoc labels. 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 opens with 'Fetches metadata for an EU legal act', which is a specific verb and resource. It clearly enumerates the metadata types (dates, in-force status, authors, legal basis, EuroVoc descriptors, directory codes) and distinguishes this from a full-text fetch or search 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 gives clear context on how to invoke the tool: identify an act by celex_id, eli, or oj_ref and provide exactly one, with optional language. It does not explicitly name sibling tools or state when not to use it, but the lookup semantics are sufficiently clear from the wording.

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 behavior beyond the annotations: it explains that matching is a contiguous, case-insensitive phrase (not tokenized full-text), and that results are newest-first within the fetched sample, not necessarily globally newest for broad queries.

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 succinct yet information-dense, consisting of multiple short clauses that cover the main purpose, usage caveats, language support, and result ordering without unnecessary verbosity.

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 presence of an output schema and the detailed parameter descriptions, the tool description is complete for an agent to decide when and how to use it, including performance hints and result ordering nuances.

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?

Although the schema already provides descriptions for all parameters, the description adds extra semantic clarity, such as instructing users to match the query term to the chosen language and explaining that language applies to both title and full text.

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 EU legal acts by title substring, and explicitly differentiates it from eurlex_by_eurovoc for topic-based discovery. The verb and resource are unambiguous.

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

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

It provides explicit guidance on when to use this tool versus the alternative (topic-based discovery via eurlex_by_eurovoc) and advises narrowing broad queries with resource_type or date filters to avoid slow performance.

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 annotations already declare readOnlyHint/openWorldHint/idempotentHint/destructiveHint, and the description reinforces and expands on them: only SELECT/ASK are accepted, SPARQL Update and federated SERVICE are rejected, LIMIT is auto-appended or capped, and response truncation is described. The example and type note about xsd:string literals add concrete behavioral detail.

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

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

The description is long but every sentence carries meaningful operational detail; it is organized from purpose to constraints to output and example. It is slightly repetitive with the input schema description, but not padded enough to lose clarity.

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

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

For a raw query execution tool, the description covers what the tool does, when to use it, what queries are allowed, what happens with LIMIT, what the response looks like (SPARQL JSON, row_count, truncated flag), and how to correctly compare CELEX/ELI literals. An agent has enough information to use it correctly without external context.

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

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

The single query parameter is thoroughly documented: it includes min/max lengths, restrictions on query forms, the automatic LIMIT behavior, the CDM ontology context, a concrete example query, and the CELEX/ELI string-matching caveat. This goes far beyond the schema's basic property description.

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

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

States a specific verb ('run a raw, read-only SPARQL 1.1 query') and a specific resource ('EU Publications Office (Cellar) endpoint'). It explicitly frames itself as an escape hatch for when higher-level tools cannot express the need, distinguishing it from the sibling 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?

Explicitly says to use this when higher-level tools cannot express what is needed, and directs the agent to read the eurlex_guide prompt first for ontology knowledge. It also clearly states the allowed query forms, the automatic LIMIT behavior, and the rejection of UPDATE/SERVICE clauses.

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 language-specific offsets, the dependency on plain text, the 300-entry cap with truncation flag, and the heading-recognition coverage, all beyond the read-only annotation. It also explains the paragraph-number detection logic for judgments, giving the agent accurate expectations.

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

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

The description is richly informative but remains focused, covering purpose, usage, and key behavioral details without extraneous content. It is structured with clear separators, making it easy to scan. Slight repetition of parameter constraints is minor and acceptable.

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

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

The description covers the tool's output structure, usage scenario, language handling, size limits, and case-law extensions, leaving no major gaps. It even specifies the follow-up call pattern, ensuring the agent knows how to apply the offsets.

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?

While the schema already describes all parameters, the description adds the crucial note that offsets are language-specific and advises passing the same language to the follow-up fetch call. It also clarifies the relationship between celex_id, eli, and oj_ref, requiring exactly one, which is echoed but reinforced.

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 the outline (table of contents) of an EU legal act with character offsets, distinguishing it from other document tools. The verb 'returns' and the specific resource make 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?

It explicitly advises using this tool as a map for targeted reading, telling the agent to read an article's offset and follow up with eurlex_fetch. This gives clear when-to-use guidance, including the special case of case-law paragraphs.

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 aligns with the annotations (readOnlyHint, idempotentHint, destructiveHint) and adds behavioral details not covered by annotations: pagination behavior ('pass the previous response's next_offset to continue'), selection of the most current summary, and the 'no summary' message. 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 a single, well-structured paragraph that leads with purpose, then input/output details, pagination, edge cases, and ends with alternative tools. It contains no redundancy and all information is directly 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?

The description covers the full context: input format, output contents (summary text, id, title, date, flag, source_url, other_summaries), pagination, edge cases (no summary, multiple summaries), and sibling tools. It is complete for an agent to know when and how to use this tool.

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

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

All four parameters (celex_id, language, offset, max_chars) are explained in the schema. The description adds semantic layer: celex_id examples, language availability across 24 EU languages, and pagination 'exactly like eurlex_fetch'. This enriches the schema descriptions, which already had 100% coverage.

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

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

The description clearly identifies the tool's function: 'Returns the EU's official plain-language summary (LEGISSUM) of a legal act'. It distinguishes this from the binding legal text and explicitly contrasts with sibling tools (eurlex_fetch for full text, eurlex_metadata for metadata), 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?

The description provides explicit usage guidance: 'For the full legal text use eurlex_fetch; for structured metadata use eurlex_metadata.' It also explains when no summary is available and that the most current non-obsolete summary is returned, giving clear conditions for 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?

The description adds meaningful behavior beyond the annotations: it discloses that titles are returned as-is in the member state's own language, that total_found reports the full count while results are capped, and that omitting country returns all member states. These details complement the readOnlyHint and idempotentHint annotations.

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

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

The description is comprehensive yet tightly structured, with no redundant sentences. Each sentence conveys a distinct fact (purpose, input, filter, output, language caveat, exclusions). It is long but every part is informative.

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 (4 parameters, enums, output schema), the description provides all necessary context: what the response contains (total_found, results), how filters behave, examples for celex_id, and clear boundaries versus sibling tools. Nothing an agent needs is 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 coverage is 100% and the description enriches each parameter: celex_id includes pattern and examples, country explains the EU-specific 'EL' exception, language clarifies it does not translate titles, and limit is described in the schema. The description adds real semantic value beyond the raw 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 national implementing measures for a given EU directive, phrased as the answer to a concrete question. It distinguishes from siblings by noting that regulations/decisions have no NIMs and directing the directive itself to eurlex_fetch/eurlex_metadata.

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 guides when to use this tool (transposition/compliance tracking) and when not to (regulations/decisions; directive itself via other tools). It also clarifies the optional country filter and the language field's non-translation caveat.

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