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

Beyond the annotations (readOnly=false, destructive=false, idempotent=false), it discloses that new subtasks are appended at the end of the task and that title is mandatory in add mode, plus that rename is a valid mutation. It does not warn about the non-idempotent consequence (repeated calls without subtask_id create duplicates) or what error occurs if title is omitted with subtask_id, which matters given idempotentHint=false.

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?

A single front-loaded sentence built around the decisive condition, with two short parentheticals that each add non-redundant information (title required, where IDs live). No filler, no restatement of the tool name or title.

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 four-parameter mutation tool with full schema coverage and a clear safety profile in annotations, the description covers the operation, both modes, and ID discovery. It leaves minor gaps around return values and failure conditions, which is acceptable since there is no output schema to lean on but also no complex payload to explain.

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 100%, so parameter meaning is already largely carried by the schema. The description adds the mode-switch semantics of subtask_id (absent = create, present = modify) and reinforces title's role as rename payload, but is_completed's meaning is already fully documented in the schema, so added value is modest and the baseline 3 applies.

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 (ajouter/modifier une sous-tâche) and splits the behavior into two clearly named modes keyed on subtask_id: append to the end of a task, or check/uncheck/rename an existing one. An agent can tell immediately that this is the subtask-level write tool rather than the task-level dandori_save or dandori_create_task.

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?

It gives explicit conditions for each mode ('Sans subtask_id' vs 'avec') and points to dandori_list_tasks as the place to obtain the IDs, which is the crucial routing hint for a tool that requires an opaque identifier. It stops short of stating exclusions or prerequisites, such as where task_id itself comes from or when to prefer a task-level save.

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