LibreJustice

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

Despite strong annotations (readOnly, non-destructive, idempotent), the description adds substantial behavioral context: citation formatting details, the meaning of appellateFate, the scope of caseChronology, and the caveat that absence does not prove non-existence. No contradiction with 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 densely informative yet compact, with each sentence conveying a distinct aspect (content, link handling, metadata fields, caveats). No filler or 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 single parameter, strong annotations, output schema presence, and sibling context, the description covers key usage details, metadata semantics, and important caveats, making it fully sufficient for an agent to invoke 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 100% and the url parameter description already explains its origin (search_decisions hit or inline citation) and fallback. The tool description mostly repeats this, adding no new semantic 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 states a specific verb ('Fetch') and resource ('full text and metadata of a decision by its url'), clearly distinguishing it from siblings like get_legal_text for articles and search_decisions for querying. It also explains the inline link behavior, reinforcing what this tool uniquely does.

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 instructs to use search_decisions first when lacking a URL, and clarifies when get_legal_text vs get_decision is appropriate for inline links. This provides direct guidance on tool selection and 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?

Annotations already declare readOnly=true and idempotent=true, and the description adds significant behavioral detail: returns the in-force version at a date, includes the timeline of all versions, inline markdown links to cross-referenced articles point to the same date, and commentaires carry institutional commentary. This exceeds annotation coverage and clarifies important side-effects-free 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 tightly written with three sentences, each carrying substantive information: main functionality, link behavior, and coverage scope. It could be slightly more concise, but no sentence is wasted and the structure front-loads the core 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?

For a tool with an output schema, the description goes beyond requirements by explaining return content (full text, status, validity dates, timeline, commentary), cross-referencing behavior, and coverage. Even with annotations and schema present, this provides complete operational understanding for an AI agent.

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

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

Schema description coverage is 100%, with the url and date parameters already well documented. The description adds no new parameter-level semantics beyond what the schema provides, but it does reinforce the URL construction and date omission. Baseline 3 is appropriate because the schema does the heavy lifting.

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 a precise verb and resource: "Fetch a statutory article as it read on a given date, by its `url`." It explicitly scopes the tool to /texte/ links and distinguishes it from search tools like search_legal_texts by focusing on retrieval of a single known article rather than discovery.

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: use it to fetch article versions by URL, omit date for current version, and open cross-referenced links with this same tool. It mentions that URLs come from search_legal_texts hits or citation links, but does not explicitly state when not to use it compared to get_decision or other siblings.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint (false). Description adds ordering (most recent first), which tabs populate, and interpretation of lastSource in readingHistory. 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?

Well-structured with core purpose first. Each sentence earns its place. Slightly verbose on readingHistory detail but overall 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 output schema exists, description needn't detail return values. Covers kind and limit semantics, account requirement. Adequately complete for a list 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 100% (baseline 3). Description adds meaning: what each kind returns (structured filters, summary, URL chain) and default behavior. For limit, it adds minimal 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?

Description clearly states 'List the authenticated user's own activity, most recent first.' Specifies resource (activity) and verb (list). Distinguishes from siblings like get_decision by mentioning chaining via URL.

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?

Explains when to use (to list activity) and how to select tabs via kind. Implicitly contrasts with get_decision for specific decisions, but lacks explicit when-not-to-use or comparison with other siblings like search_decisions.

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 declare readOnlyHint=true and idempotentHint=true, so the bar for adding value is high. The description discloses that aiSummary is 'a machine paraphrase never quotable as the court's words', explains the facets block, and clarifies filter combination logic (OR within, AND across). These are behavioral traits beyond the structured 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 front-loaded with the primary purpose and then adds only high-value behavioral and usage details. Each sentence covers a distinct aspect (result shape, query/filter split, OR/AND semantics, facet reuse), with no redundant filler. It is dense but appropriately sized for the tool's complexity.

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 18 parameters and an output schema, the description focuses on the critical decision logic: how to partition query vs filters, how results are presented (aiSummary vs snippet), and how to refine via facets. It also points to get_decision for the full text, covering the main agent workflow. The output schema covers return values, so the description need not repeat them.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds cross-cutting parameter semantics: values within a single filter are OR'd, different filters are AND'd, and facet keys from the response can be reused verbatim as parameter values. This global logic is not evident from individual parameter descriptions, adding meaningful 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 opens with 'Search decisions by meaning and keywords combined', clearly stating the tool's function. It distinguishes from sibling tools by noting 'get_decision reads the full text' and describing the shortlist output. The guidance to 'Put constraints in the structured filters... keep the query for the legal issue' further reinforces the tool's role.

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 names get_decision as the follow-up for full text, giving the agent a clear when-to-use vs. compromise. It provides actionable rules: keep constraints in filters and the legal issue in the query, with OR/AND semantics and facet reuse for refinement. This is explicit guidance relative to the alternative tool.

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 annotations already marking readOnlyHint=true and idempotentHint=true, the description adds substantial behavioral context: returns a ranked shortlist with highlighted snippets and exact total, includes a facets block to reuse verbatim, applies alias expansion, and shares date semantics with get_legal_text. 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?

Four sentences, each earning its place: purpose, query guidance, facets, and chaining. Front-loaded with the core purpose and no redundancy. The density is appropriate for a search tool with this complexity.

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 purpose, query formulation, filters, facets, chaining behavior, and date semantics. Despite having an output schema, the description adds valuable usage context (highlighted snippets, total, facets reuse) that makes the tool self-contained and actionable.

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 schema coverage is 100%, the description adds meaning beyond schema: it clarifies query language, explains how to use the code filter with slugs/exact names, instructs reusing facet keys verbatim, and specifies date semantics for earlier versions. This significantly enriches parameter 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?

The description opens with a specific verb and resource: 'Find statutory articles from their subject or wording when the article number is unknown.' This clearly distinguishes it from siblings like search_decisions (which searches court decisions) and get_legal_text (which retrieves a specific article by ID).

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

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

The description states when to use it ('when the article number is unknown') and provides concrete usage guidance: query in French, put the code in the code filter, keep the query for the subject. It also explains chaining into get_legal_text. It does not explicitly name alternatives for 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.