add_event

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

Annotations already declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, so the write/safety profile is covered. The description goes well beyond that: it specifies the unified return object, Europe/Paris local-time semantics, all-day inclusion rules, the container default, RRULE prefix conventions, and the concrete consequence of tracked=true (occurrences behave as tasks and go overdue).

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 critical constraint is front-loaded before any format detail, which is exactly right. It is dense but nearly every clause carries operational meaning; only the explicit 'Renvoie l'objet résultant au format unifié' is weakly redundant given an output schema exists.

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 9-parameter mutation tool with an output schema and rich annotations, the description covers the non-obvious surface: timezone, all-day range semantics, recurrence format, and tracked behavior. Return values need no explanation since an output schema is present.

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 0%, so the description must carry the load, and it does for the hard parameters: start/end format, all_day boundary semantics, container default, recurrence RRULE shape with examples, and tracked behavior. title, notes, and location are left to inference, but they are self-evident, so this is a minor gap rather than a real one.

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 names a specific verb and resource ('Crée un événement') and adds scope-relevant detail that separates it from siblings like update_event or add_task. Nothing about the intent is ambiguous, and the leading French warning makes the tool's identity and gating unmistakable.

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?

Explicitly states when to use it and when not to: only on Denis's explicit request, never on the agent's own initiative, not even to 'help' or 'correct'. This is a rare case of a tool giving a hard behavioral gate with the exclusion condition spelled out.

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