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

Beyond the readOnlyHint/idempotentHint annotations, the description adds meaningful behavioral detail: it returns exact price when fixed, a min/max range when cost depends on channel or outcome, does not promise an accuracy percentage, and warns the agent to check cost_range. It also discloses operational characteristics: 'COST: free - no key required' and 'LATENCY: ~100ms.' 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?

The description is well-structured and front-loaded: the first sentence states the core purpose, followed by pricing behavior, an accuracy caveat, and practical usage guidance. The examples are compact but illustrative, and every section (WHEN TO USE, WHEN NOT TO USE, COST, LATENCY) adds operational value without padding.

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?

With no output schema, the description carries the burden of explaining return values, and it does so clearly: cost estimate with exact/range behavior, latency estimate, success-probability estimate, and the cost_range field to check. It also covers when to call, when not to, cost, latency, and parameter examples. For a simple two-parameter preview tool, nothing essential is missing.

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 schema description covers only params ('The same request body you would pass to the operation'), leaving operation undocumented. The tool description compensates with concrete examples mapping operation values like 'send_message' and 'schedule_appointment' to realistic params, clarifying that operation names the target call and params mirror its request body. Still, the operation parameter semantics remain partially implicit.

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-resource pair: 'Return an expected cost estimate, latency estimate, and success-probability estimate for a proposed call before execution.' It clearly identifies the tool as a pre-execution preview, which separates it from execution tools like send_message or schedule_appointment. However, it does not explicitly differentiate from closely related sibling tools such as check_quota, so it stops just short of full sibling distinction.

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?

WHEN TO USE and WHEN NOT TO USE are explicit: 'Use before any operation when the agent is operating under a budget constraint and needs to decide whether to proceed' and 'Do not use in a hot loop — cache the result for at least 60 seconds.' This provides clear context and exclusion criteria, including a caching strategy instead of repeated calls.

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