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

The annotation readOnlyHint=true indicates no data mutation, and the description adds behavioral context by explaining that the tool adjusts response style without affecting source discipline. This goes beyond the annotation by clarifying the scope of the state change, which is useful. It does not elaborate on persistence, but that is minor for a mode setter.

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

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

The description is relatively long but each sentence is purposeful: it front-loads the primary purpose and then systematically explains each mode. The structure with colons and quotes is clear. It earns its length because the mode explanations are essential for correct invocation, though it could be slightly more terse.

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 a single enumerable parameter and no output schema, the description is complete. It covers what the tool does, when to use it, and what each mode means. The usage trigger is explicit, and the mention of 'without touching source discipline' addresses a potential concern. Nothing critical 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?

The schema covers 100% of parameters and describes 'niveau' as 'Le mode à activer,' but the description adds substantial meaning by explaining each enum value ('debutant', 'classique', 'avance') in detail, including target audience and style. This goes far beyond the basic schema, enabling the agent to select the correct 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 tool's function: it sets the response register based on the reader, and it explicitly details three modes without touching source discipline. This is a specific verb and resource that distinguishes it from sibling tools like 'sefaria_search' or 'guide_paracha', which are content-retrieval tools rather than mode setters.

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 an explicit trigger: 'À charger dès que le niveau de l'utilisateur est connu ou déductible.' This tells the agent when to invoke the tool. It does not provide explicit negative cases or alternatives, but since this is a global mode setter with no obvious alternative, the guidance is adequate.

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