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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description reveals critical behavioral traits: decision requests are BLOCKING, the operator is waiting, the response includes a pre-filled nextActions array, and authentication is required. This adds meaningful context about side effects and workflow that annotations alone do not capture.

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 well-structured and information-dense, beginning with a purpose sentence, followed by 'Mechanism:', examples, triggers, response details, and next steps. Each sentence serves a distinct purpose, and the format makes it easy to scan, especially for a tool with a blocking mechanism and workflow implications.

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?

Despite no output schema, the description explains the key return elements (nextActions array with resolve_decision_request actions, pre-filled decisionId and questionCode). It also covers triggers, examples, blocking behavior, and the follow-up action, making the tool's role in the overall workflow clear. This is highly complete for a simple two-parameter read tool.

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?

The input schema covers 100% of parameter descriptions (apiKey and taskId). The description does not add additional parameter-level semantics beyond schema, though it mentions 'Requires authentication' which loosely connects to apiKey. The schema already provides the necessary detail, so the description contributes minimal added value here.

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 begins with a clear, specific statement: 'Get pending decision requests for a task.' It distinguishes itself from related sibling tools by focusing on 'decision requests' and mentioning the companion 'resolve_decision_request' action. The detailed explanation of what decision requests are (questions from platform/operator) further clarifies the tool's exact purpose.

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 explicit triggers for when to use the tool ('task.decision_requested webhook event' or seeing the count in get_pending_actions.decisionRequests.count) and clearly states the next step ('Next: resolve_decision_request'). It does not explicitly state when *not* to use it or name a competing alternative tool, but the context is strong enough for an agent to determine appropriate usage.

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