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

Annotations already indicate idempotency and non-destructiveness, but the description adds a meaningful non-obvious side effect: it 'may renew and persist an expired artifact download link.' It also discloses the polling rate constraint. No contradiction with annotations exists.

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?

Three short sentences deliver essential behavior, side effects, and polling guidance with no filler. The most important purpose is front-loaded, and every sentence adds value.

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?

The tool has an output schema, so return values need not be described. The description covers ownership, polling behavior, side-effect potential, and the artifact link renewal behavior, making it complete for safe invocation.

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 task_id as 'Job ID returned by start_task.' The description does not add further parameter-level meaning, so the baseline of 3 is appropriate.

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 uses a specific verb ('read') with a clear resource ('progress and final result of a durable job') and adds ownership scope ('owned by this connection'). It is clearly distinguished from sibling tools like start_task and cancel_task, which create or terminate jobs.

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 gives clear usage context: this is the polling endpoint for a durable job, and it explicitly instructs 'poll no sooner than the returned interval.' It does not explicitly name alternatives or state when not to use it, but the context is unambiguous enough for an agent.

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