Poll Task

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

With no annotations, the description carries the disclosure burden well: it names the polling interval, the default unbounded timeout, the terminal states, and the strong agent-side restriction on invocation. It does not say what is returned when timeout_seconds expires, which is the one remaining behavioral gap.

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?

Front-loaded and functional, but the 'only when user explicitly asks' rule is stated twice (in the parenthetical title line and again in the ⚠️ block, restated in both Chinese and English), which is redundant space.

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?

An output schema exists, so return values need not be described. The blocking/polling behavior and invocation guardrails are covered; only the 'server' parameter's meaning and the post-timeout outcome are left open.

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 0%, so the description must compensate. It clarifies timeout_seconds (caps total polling duration, default null = no limit), but says nothing about the 'server' parameter, leaving the target-server selection ambiguous.

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 — polling a task until it reaches a terminal state — and adds the distinguishing behavioral detail (20s interval, completed/failed/cancelled). This is clearly separable from siblings like get_task (single check) and cancel_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?

Explicitly says when to use (user explicitly asks to wait/poll, with example utterances) and when not to (agent must not call proactively; ask the user instead). No inference required.

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