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

No annotations are provided, so the description must carry the burden. It discloses that the tool returns time-series data and insights, but does not mention read-only nature, rate limits, or other behavioral traits.

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

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

Two concise sentences, front-loaded with the core purpose and outputs. 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?

With no output schema, the description explains return format (time-series, insights). It covers the main functionality, though it omits mentioning the optional filters parameter.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds no additional meaning beyond the schema, only repeating 'Supports year/quarter/month granularity' which is already an enum.

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 analyzes temporal trends in case law and returns time-series data with insights. However, it does not distinguish from similar siblings like cases_get_statistics, which might also analyze trends.

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

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

No explicit guidance on when to use this tool over alternatives, nor when not to use it. The description only implies usage for temporal analysis.

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; description only mentions max 100 and single request, but does not disclose idempotency, error handling, or that it is a read operation. Minimal behavioral disclosure 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?

Two sentences, no wasted words, front-loaded with the core action. Efficiently communicates the tool's purpose.

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

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

No output schema; description does not explain the return format or behavior (e.g., order preservation, error handling). Adequate for a simple tool but could be more complete.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds no new meaning beyond what the schema provides, so baseline 3 is appropriate.

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

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

Description clearly states the action (batch retrieve), resource (cases by ECLI identifiers), and distinguishes from sibling tools like cases_get_by_ecli by emphasizing efficient multiple-case retrieval.

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

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

Implies usage for fetching many cases efficiently with a max of 100, but lacks explicit when-not-to-use or alternative comparisons. However, the sibling context provides clear differentiation.

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 clearly states the tool compares metadata, subjects, and procedures, and returns a divergence score between 0 and 1. This sufficiently discloses the behavior, though it does not explicitly state it is read-only.

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 with no extraneous content. Front-loaded with the core action ('Compare multiple cases side-by-side') followed by specifics. Every sentence is necessary.

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

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

Given no output schema, the description explains the return value (divergence score). It would be more complete if it also described the format of the side-by-side differences, but the core functionality is covered. The high schema coverage and clear parameters help.

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 value beyond schema by specifying that comparisons cover 'metadata, subjects, and procedures,' which are examples of what 'comparison_aspects' can include. This aids interpretation.

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 uses a specific verb ('compare') and resource ('multiple cases'), and explains the output (divergence score). It distinguishes this tool from siblings like cases_get_similar by focusing on side-by-side comparison and explicit scoring.

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

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

The description implies use for comparing cases side-by-side but does not explicitly state when not to use it or mention alternatives like cases_get_similar for similarity search. Guidance is adequate but lacks 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?

No annotations are provided, so the description carries the full burden. It discloses the tool enriches queries with legal terms and returns structured terms, but it does not explain the internal process, idempotency, or whether external resources are used. The behavioral disclosure is adequate but not detailed.

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

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

The description is two sentences, front-loaded with the tool's purpose, and every word contributes meaning. No unnecessary 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 tool has only one parameter and no output schema or annotations, the description is mostly complete. It explains the action and the return. However, it could clarify the output format (e.g., JSON structure) and explicitly state the language requirement (Dutch).

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 'query' is described in the schema as 'Raw user question' with 100% coverage. The tool description adds no extra semantic details beyond the schema, such as expected language or format. Baseline 3 applies as schema covers the parameter.

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 expands a user query with Dutch legal synonyms, abbreviations, entities, and temporal hints, and specifies the return of structured must/should terms. This clearly distinguishes it from sibling tools like cases_search or cases_extract_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 implies use before search for better retrieval but provides no explicit guidance on when to use this tool versus alternatives such as cases_rerank or cases_search_by_article. There are no when-not-to-use notes or prerequisites mentioned.

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

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

With no annotations, the description must disclose behavioral traits. It states it uses regex for Dutch legal text, but does not explain safety (e.g., read-only vs mutation), permissions, failure modes, or limitations. Critical context for a tool that processes case data is missing.

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

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

The description is two sentences and front-loads the purpose, followed by a key detail about regex and language. Every sentence adds value, and no words are wasted.

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 should explain the return format. It only lists entity types but not how they are returned (e.g., list, map). Does not mention pagination, ordering, or error conditions. Incomplete for a tool with 2 parameters and no output 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?

The schema already describes both parameters (ECLI identifier, entity types) with 100% coverage. The description adds example entity types ('cited cases, legal articles, monetary amounts, dates, and parties'), providing useful context beyond the schema. However, it does not specify the expected format for entity_types 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 states the verb 'extract entities from a case' and specifies the types of entities (cited cases, legal articles, monetary amounts, dates, parties). It distinguishes from sibling tools like 'cases_get_citations' and 'cases_get_by_ecli' which have different purposes.

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

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

The description mentions it uses regex for Dutch legal text, implying it's for Dutch cases, but does not explicitly state when to use this tool vs alternatives like 'cases_get_citations' or 'cases_get_by_ecli'. No when-not or alternative guidance is provided.

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

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

With no annotations, the description discloses that it returns normalized metadata and paragraph-level anchors, implying a safe read operation. However, it does not explicitly state idempotency, auth requirements, or rate limits. It adds some value beyond annotations but not comprehensive.

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

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

The description is a single sentence that front-loads the main action and key details (ECLI, structured sections). No extraneous words, 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?

For a simple 2-parameter tool with no output schema, the description adequately explains what is returned and the optional parameter. It is complete enough given the complexity and sibling 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?

Schema coverage is 100% with descriptions for both parameters. The description adds context by explaining the return format (structured sections and paragraph-level anchors) and that section_selector can retrieve specific sections, enhancing understanding beyond the schema alone.

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 ('Retrieve'), the resource ('a specific case'), and the unique identifier ('ECLI'). It also mentions structured sections and paragraph-level anchors, which distinguishes it from sibling tools like cases_search or cases_bulk_get.

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

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

No explicit guidance on when to use this tool vs alternatives. While it's clear from the description that this is for fetching a single case by ECLI, it does not provide when-not-to-use scenarios or mention other tools for similar tasks.

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

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

No annotations are provided, so the description bears full burden. It discloses that both outgoing and incoming citations are returned with context snippets, but does not mention side effects, authorization needs, rate limits, or behavior for edge cases like missing citations.

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, precise and front-loaded. Every sentence adds meaningful 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 3 parameters, no output schema, and no annotations, the description explains the core functionality and return types but lacks details on return format, pagination (if any), or how to interpret context snippets. It is adequate but not fully complete.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the meaning of the results (outgoing vs incoming) and the include_context parameter. However, it does not elaborate on the enum values for direction beyond what the schema provides.

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 uses the specific verb 'Extract' and clearly identifies the resource 'citations from a case'. It distinguishes between outgoing and incoming citations, which differentiates it from sibling tools like cases_get_similar or cases_get_by_ecli.

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

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

The description does not provide explicit guidance on when to use this tool versus siblings. It implies usage for citation extraction, but lacks when-not-to-use or alternative recommendations, which is needed given many sibling tools.

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

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

No annotations are provided, so the description carries full burden. It discloses return values (case counts, date ranges, top subjects, procedures) but lacks details on side effects, data limits, or error conditions.

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

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

A single clear sentence front-loads the key action and outcomes, with 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 no output schema and 4 parameters, the description covers the main output fields but could be more complete by explaining date formats or 'top subjects' details.

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

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

Schema coverage is 100%, so baseline 3. The description adds minimal new meaning beyond the schema, mostly restating the function purpose without deepening parameter semantics.

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

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

The description clearly states the tool compares statistics across multiple courts for a query, distinguishing it from siblings like cases_search or cases_get_statistics which serve different purposes.

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

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

The description implies when to use (comparing court statistics) but does not explicitly state when not to use or mention alternatives among the many sibling tools.

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

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

No annotations provided, so description carries burden. Names the algorithm and filtering, but does not explain how similarity is computed, performance limits, or return format details beyond parameter 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?

Two sentences, front-loaded with core purpose, second adds filtering. No redundant information.

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

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

No output schema, but description hints at return of similar cases. Parameters are well-covered via schema and description. Could specify sorting by similarity or scoring, but adequate for a simple retrieval tool.

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

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

Schema coverage is 100%, baseline 3. Description adds context that ecli is the source case and that content matching uses paragraphs and summary, which is not in schema, enhancing understanding.

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 verb 'Find similar cases', resource 'cases', algorithm 'MoreLikeThis', and basis 'paragraphs and summary', distinguishing it from sibling tools like cases_search or cases_get_by_ecli.

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

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

Implies usage when a source case (by ECLI) is available and similar content is desired, but lacks explicit when-not-to-use or alternatives like cases_search for keyword matching.

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

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

No annotations are provided, so the description must disclose behavioral traits. It only describes the output (statistics) but does not mention if the operation is read-only, any authentication requirements, rate limits, or side effects. For a statistics tool, destructiveness is unlikely, but transparency is lacking.

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

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

The description is a single, front-loaded sentence of 16 words, efficiently conveying the tool's purpose and outputs without superfluous information.

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

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

The description covers the main outputs (facets, date ranges, counts) and is adequate for a tool with 3 parameters (one required) and no output schema. It could mention the query parameter, but the schema already defines it. Overall, it is sufficiently 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 description coverage is 100%, so baseline is 3. The description adds context by mentioning 'facet distributions (courts, legal areas, procedures)' and 'date ranges', which relate to include_facets and filters parameters. However, it does not explain each parameter individually or their formats 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's purpose ('Get comprehensive statistics for a search query') and lists specific outputs (facet distributions, date ranges, aggregate counts). It distinguishes this tool from sibling tools like cases_search (raw results) and cases_analyze_trend (trend analysis).

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

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

The description implies use for obtaining statistical aggregations but does not explicitly state when to use this tool versus alternatives (e.g., cases_get_court_stats for court-specific stats). No when-not guidance or prerequisites are provided, leaving the agent to infer usage context.

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

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

No annotations provided, so description carries full burden. It discloses output format (paragraph-level snippets with anchors) and query relevance, but lacks details on authentication, rate limits, or other behavioral traits.

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

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

Two sentences, front-loaded with verb ('Extract'), no fluff. Every sentence adds value: the first states action and resource, the second describes output and use case.

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 explains return type and structure. Parameters are fully covered by schema. However, with many sibling tools, some usage guidance would improve completeness. Still, it's nearly complete for a simple retrieval tool.

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

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

Schema coverage is 100%, so baseline is 3. The description adds minimal parameter meaning beyond schema (e.g., 'query' is already described). The description focuses more on output than parameters.

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

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

The description clearly states the tool extracts relevant passages from a specific case for a query, returns paragraph-level snippets with anchors. It distinguishes from siblings like cases_get_by_ecli (full case) and cases_search (cross-case search) by focusing on compact context assembly.

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 hints at usage ('ideal for compact context assembly') but does not explicitly state when to use this tool versus alternatives. No mention of when not to use or prerequisites.

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

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

With no annotations, the description carries the full burden. It discloses that the tool is non-destructive (reranking) and describes the output format. However, it does not specify any potential limitations or side effects.

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

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

The description is a single concise sentence that front-loads the action and clearly communicates the core functionality without redundant information.

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

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

The description adequately explains inputs and outputs for a reranking tool given no output schema. It covers the main purpose and return format. A minor improvement could be stating the output is a reranked list, but it is already sufficiently clear.

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

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

Schema coverage is 100% with descriptions for both parameters ('Search query' and 'ECLI identifiers to rerank'). The description adds no additional semantic context for the parameters beyond what the schema provides. Baseline 3 is appropriate.

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

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

The description clearly states the tool reranks cases by relevance using a query and ECLI identifiers, and mentions the output of calibrated scores with original ranks. It distinguishes from sibling tools like cases_search and cases_get_similar by specifying the reranking action.

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

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

The description implies usage for refining an existing list of cases but does not explicitly state when to use this tool vs alternatives like cases_search or cases_get_similar. No exclusion criteria or alternative tool mentions are provided.

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

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

The description mentions behavioral features like 'advanced query expansion, faceting, and snippet highlighting' which aid in understanding outcomes. However, it does not disclose read-only nature, pagination behavior, or performance implications. With no annotations, the description partially carries the transparency burden but lacks completeness.

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, front-loaded sentence that efficiently conveys the core functionality and key features. No unnecessary words, and it provides a clear overview 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 rich schema (5 parameters, 100% coverage) and no output schema, the description adequately covers input semantics but lacks output details (e.g., return format explanation) and differentiation from 15 sibling tools. It is minimally complete for a search tool but leaves gaps in agent decision-making.

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

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

Schema coverage is 100%, so baseline is 3. The description adds context by summarizing filters (court, date range, area of law, procedure type) that map to the filter parameter, and hints at query expansion behavior. However, it adds little beyond what the schema already defines for each parameter, maintaining the baseline.

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 Dutch court cases with advanced features (query expansion, faceting, snippet highlighting) and supported filters. While it doesn't explicitly differentiate from siblings like cases_search_by_article, the purpose is well-defined and specific enough for an agent.

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

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

No guidance on when to use this tool versus alternatives (e.g., cases_search_by_article for article-specific searches). The description lists capabilities but doesn't provide context for selection or exclusion, leaving the agent to infer usage scenarios.

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

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

No annotations provided; description mentions it returns cases with context snippets but lacks details on read-only nature, auth needs, or rate limits.

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

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

Two efficient sentences: first defines purpose with examples, second describes return value. 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?

Adequately covers basic functionality for a search tool with 4 params, but lacks details on interpretation enum and pagination behavior that would be helpful.

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%; description adds value by giving examples for the 'article' parameter but does not clarify 'broad' vs 'narrow' interpretation or pagination beyond 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 searches for cases mentioning a specific legal article, provides examples (e.g., '6:162 BW'), and distinguishes from sibling tools like 'cases_search' which is broader.

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

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

The description implies usage when an article reference is available but does not explicitly state when not to use or compare with alternatives like 'cases_search'.

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

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

With no annotations provided, the description must fully disclose behavioral traits. It does not specify whether the tool is read-only, non-destructive, or requires authorization. As a validation tool, it likely has no side effects, but this is not made explicit.

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

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

The description is two sentences, front-loaded with the main action and output. Every word is necessary, with 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?

For a single-parameter validation tool, the description covers the core functionality and return value. However, it does not mention error handling (e.g., invalid format) or the nature of 'metadata if found', which would be helpful but not critical for such a simple tool.

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

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

Schema coverage is 100%, and the schema already describes the 'ecli' parameter as 'ECLI identifier to validate'. The description adds no new meaning beyond restating the validation purpose, so baseline 3 is appropriate.

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

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

The description clearly states the tool validates ECLI format and checks existence in the database, which distinguishes it from sibling tools like cases_get_by_ecli (which retrieves full case) and cases_search (which searches). The verb 'validate' and resource 'ECLI identifier' are specific.

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

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

The description implies use for validation and existence check, but does not explicitly state when to use or not use this tool versus alternatives. No exclusions or prerequisites are mentioned, leaving some ambiguity for the agent.

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

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

With no annotations, the description carries the full burden. It indicates a read operation ('check', 'returns'), but does not explicitly state it is non-destructive or safe, nor mention any authentication requirements. Minimal disclosure.

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

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

The description is a single sentence that efficiently conveys the purpose and scope. No wasted words, but could be slightly more 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 zero parameters, no output schema, and no annotations, the description adequately explains what the tool checks (system health, Solr, rate limits, cache) and what it returns (version and metrics). Complete enough for its simplicity.

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

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

No parameters exist, and schema coverage is 100% (empty object). The description does not need to add parameter meaning; baseline 4 is appropriate.

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

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

The description clearly states the tool checks system health, listing specific components (Solr connection, rate limits, cache statistics). It is distinct from sibling tools that are all case-related.

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

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

No explicit guidance on when to use or alternatives, but the context of sibling tools being case-related implies this is for system monitoring. Lacks when-not scenarios.

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