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

Beyond the annotations, the description discloses meaningful behavior: the task runs server-side so the agent does not need to keep anything running, notifications only fire when the result changes, a workspace token is required for later management, and the beta is subsidized with cost and capacity caveats. This significantly exceeds what annotations alone convey.

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 description is longer than average, but nearly every sentence earns its place: the core purpose is front-loaded, followed by behavioral context, kind definitions, an auth requirement, and cost information. The kind list is dense but necessary for disambiguation. Slight redundancy exists in the kind examples, but overall it is well structured.

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?

Given the output schema exists and the input schema has 100% parameter coverage, the description supplies the remaining context an agent needs: auth token requirements, cost/capacity limits, the meaning of each kind, and the notification behavior. Nothing critical is missing for selecting and invoking 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%, but the description adds valuable semantics beyond the schema by explaining what each kind means (e.g., watch_reachability tracks mainland China reachability, pipeline produces proof-carrying work orders). The input parameter meaning is also clarified across the different kinds, so the description compensates well even though the schema already documents each parameter.

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 opens with a specific verb and resource: 'Create a task that runs on a schedule in our cloud.' It then enumerates the exact kinds of tasks it supports, which distinguishes it from sibling tools like delete_task, list_tasks, and get_task_runs. The purpose is unambiguous and self-contained.

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 description provides clear context about when to use each task kind, including watch_page, daily_answer, watch_reachability, and pipeline, and references create_pipeline for pipeline tasks. It does not explicitly state when not to use the tool or name alternatives for managing tasks, but the context is strong enough for an agent to select it appropriately.

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