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

With annotations present, this adds real context beyond them: required auth scopes (jobs:read or documents:generate), the cost guarantee ('no new request or duplicate charge'), and the side-effect disclosure ('may resume that accepted work') that explains why readOnlyHint is false despite idempotentHint being true. It stops short of describing completion or error statuses returned by the poll.

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 compact clauses, front-loaded with the core action, and each one carries distinct information (what to poll, cadence, auth/cost, side effect). No filler, though the clauses are telegraphic enough to require a second read.

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 polling tool with no output schema, the description supplies retry_after_seconds and the cost/auth profile, which is meaningful. It omits what a completed or failed operation returns and how the agent should interpret terminal states, leaving the polling loop only partially specified.

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?

There is one parameter, operation_id, with 0% schema description coverage and no mention in the description, so the agent gets no help on where the value comes from, its 32-hex-char format, or its lifecycle. The phrase 'an accepted search or preparation' only loosely hints at the source of the id.

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 states a specific verb ('poll') and the resource it operates on ('an accepted search or preparation'), which maps to the search_jobs and prepare_application siblings without naming them. An agent can tell this is the follower for previously-accepted async work, though the naming is indirect rather than an explicit sibling callout.

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 implies the trigger condition ('an accepted search or preparation') and the polling cadence ('follow retry_after_seconds'), so usage is reasonably inferable. However, it never states when to stop polling versus retry, nor contrasts the tool against any named alternative, so guidelines remain implicit.

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