get_articles

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

Beyond the annotations (readOnlyHint, idempotentHint), the description adds a key behavioral detail: 'Les erreurs sont isolées par référence afin de préserver les articles valides' (errors are isolated by reference to preserve valid articles). This explains failure handling, which is not captured in annotations. However, it doesn't provide much additional behavioral context beyond this, so 4 is appropriate.

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, front-loaded sentences. Each sentence serves a distinct purpose: stating the primary function, providing usage guidance, and disclosing error handling. No unnecessary words or repetition.

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 availability of an output schema and strong annotations, the description adequately covers the essential context: the batch retrieval nature, the count limit (2-5), preference after search, alternative for single article, and error isolation behavior. There are no major gaps for the agent to successfully invoke 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?

The description does not directly describe the parameter structure, and schema description coverage is 0%. However, it does add the constraint 'de deux à cinq articles exacts' (exactly two to five articles), which is not present in the schema (which only says 'array'). This provides some semantic value, but it does not explain the act_code/article_reference fields, leaving the agent to rely on the schema's brief descriptions.

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

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

The description clearly states the tool's function: 'Retourne en un seul appel le texte normatif intégral de deux à cinq articles exacts.' It specifies a verb (returns), a resource (full normative text), and a scope (two to five exact articles). It also distinguishes itself from sibling tool get_article by explicitly mentioning the batch nature for multiple articles.

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: 'À préférer après une recherche lorsque plusieurs dispositions sont matériellement nécessaires' (prefer after a search when several provisions are needed) and directly names an alternative: 'Utiliser get_article pour une seule référence' (use get_article for a single reference). This clearly states when to use this tool vs. alternatives.

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