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

Annotations already declare destructiveHint=true and readOnlyHint=false, yet the description adds substantial context the annotations cannot: the two-phase confirmation model, the returned status='confirmation_required', and the action_id/plan_token handshake required before any write occurs. This is exactly the extra behavioral detail an agent needs to avoid calling it as if it were an immediate delete.

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 destructive nature and confirmation requirement are front-loaded, which is appropriate for a high-risk tool. There is some redundancy between 'Destructive — runs only after you confirm via confirm_action' and the following CONFIRMATION sentence, but the repetition of this critical constraint is defensible.

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 single-parameter delete with no output schema, the description covers the essential risk profile and the confirmation workflow end to end. The only real gap is the accepted id format and what to do after receiving the plan_token, which are minor omissions.

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 parameter burden. It conveys that task_id identifies a caller-owned task and is passed 'by id', but it does not clarify the accepted id format despite the schema allowing either integer or string, leaving the union unexplained.

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 first sentence pairs a specific verb and resource ('Delete ... tasks') with an explicit scope constraint ('by id', 'Only the caller's own task is reachable'), so the agent knows exactly what is removed and whose data is affected. It is distinguishable from other delete_* siblings by the task resource and caller-owned scope.

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 clearly states the precondition for invocation: the caller must confirm via confirm_action, since the tool is 'PROPOSED, never performed directly.' It does not spell out when to prefer this over an alternative (e.g., a status change versus a hard delete), but the preconditions for use are unambiguous.

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