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

The description discloses meaningful behavioral detail beyond the readOnlyHint annotation: Claude becomes a study partner, asks questions, defends opposing positions (Rashi vs Tosafot), and withholds direct answers. This explains the mode's interactive design without contradicting the annotation.

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 with zero fluff. The purpose is front-loaded, and the usage guidance is tacked as a separate, clearly readable instruction. The parenthetical examples (Rashi vs. Tosafot) are efficient and illustrative.

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 no parameters, no output schema, and only a readOnlyHint annotation, the description is sufficiently complete: it tells an agent what the mode does, how it behaves, and when to activate it. It could touch on whether mode_etude coexists, but that is above the basis.

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?

With zero parameters and 100% schema coverage, the description is not required to explain parameter behavior. There are no parameters, so this dimension scores the baseline 4 as specified.

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 what the tool does: it activates an interactive study mode where Claude becomes an active study partner, asks questions, defends alternative positions, and helps formulate kouchiot. It also distinguishes this from a simple answer-returning mode, but it does not explicitly differentiate from the sibling mode_etude, which is likely a related study mode.

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 explicit when-to-use guidance: 'À charger quand l'utilisateur veut ÉTUDIER un texte, pas juste obtenir une réponse.' This provides a clear yes/no for a relevant situation. However, it does not mention when NOT to use it in favor of a specific alternative sibling like mode_etude, so it's not quite full guidance.

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