add_task

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds real behavioral context: it returns the resulting object in a unified format, and a nonexistent list_name is refused rather than created. It does not detail permission or rate-limit behavior, but for a non-destructive write this is solid.

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?

Dense but waste-free, and correctly front-loads the most decision-relevant constraint (write only on explicit request) before the mechanics. Every sentence carries information the agent needs.

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 4-parameter write tool with an output schema and safety annotations, the description covers the remaining gaps: usage constraints, parameter formats/defaults, and the refusal behavior. Nothing needed to invoke it correctly 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?

Schema description coverage is 0%, so the description must compensate, and it does for three of four parameters: due format ('AAAA-MM-JJ', optional), list_name default and refusal semantics, and a notes convention for estimated duration. Only the required title is left undocumented, which is self-evident.

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?

States a specific verb and resource ('Crée une tâche'), which an agent can distinguish from siblings like add_event (different resource) or update_task (different operation). The write framing further separates it from read tools such as tasks/agenda/overdue.

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 ('uniquement sur demande explicite de Denis') and when not to ('Ne jamais appeler de sa propre initiative, ni pour aider, ni pour corriger'). This is unusually precise routing guidance with named exclusions.

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