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

Annotations only give the generic mutation profile (readOnly=false, destructive=false, idempotent=false), while the description adds high-value behavior: it runs server-side with no client process, it stays silent unless the result actually changes, it requires a workspace token (?w=ws_...) for later management, and costs/capacity limits apply. These auth, notification, and cost traits go well beyond annotation coverage.

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?

Purpose and the no-hosting constraint are front-loaded, then kinds are listed efficiently in a single inline enumeration. It is dense but every clause carries information; the beta pricing/capacity sentence is the softest, though still relevant to invocation expectations.

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?

With an output schema present, return values need not be described, and the description covers what remains: scheduling semantics, the four kinds, notification-on-change behavior, the workspace-token prerequisite, and cost posture. An agent has everything needed to pick a kind and invoke the tool correctly.

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 coverage is 100% and the schema already documents notify_url and interval_seconds with their defaults, so the baseline is 3. The description adds genuine value by explaining what each kind consumes as 'input' (URL to watch vs question to re-research) and what kind selection implies, which the bare string-typed kind field does not convey.

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+resource ('Create a task that runs on a schedule in our cloud'), clarifies hosting responsibility ('you do not keep anything running'), and enumerates four distinct kinds with one-line explanations. This clearly separates it from siblings like list_tasks, get_task_runs, and delete_task, which operate on already-created tasks.

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 kind enumeration effectively tells the agent when each mode applies (watch_page vs daily_answer vs watch_reachability vs pipeline), including the cross-reference to create_pipeline for the pipeline kind. However, it never explicitly states when not to use this tool or routes to sibling tools for viewing/managing tasks, so it stops short of full when/when-not guidance.

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