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

The description adds behavioral detail beyond the annotations, including that the estimate may be a range when cost depends on channel or outcome, that no accuracy percentage is promised, and that the tool is free with ~100ms latency. This complements the readOnlyHint and idempotentHint annotations by clarifying what kind of result the agent can expect and how to interpret it.

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 with clear headers, a front-loaded purpose statement, and concise usage guidance. Every section adds value, including examples, cost, and latency. Despite its length, it remains scannable and directly relevant to tool selection and invocation.

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 description provides enough context for a 2-parameter tool with no output schema: it explains the return dimensions, exact vs. range behavior, and limitation on accuracy guarantees. The main gap is that valid 'operation' values are only implied through examples rather than enumerated or otherwise specified, which leaves some ambiguity for arbitrary operations. Overall, it is nearly complete for typical use.

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 coverage is 50%, with 'params' documented as 'the same request body you would pass to the operation' but 'operation' left undocumented. The examples help by showing operation values like 'send_message' and 'schedule_appointment', but the description does not explicitly define what values 'operation' accepts or how nested params should be structured. This is adequate but incomplete for full parameter understanding.

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 clearly states the tool returns cost, latency, and success-probability estimates for a proposed call before execution. It also explains exact pricing versus min/max ranges, making the tool's core function unambiguous. It is easily distinguishable from its siblings, which handle booking, status, and verification rather than pre-execution cost previews.

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 includes explicit WHEN TO USE and WHEN NOT TO USE sections, stating to use it before operations under budget constraints and to avoid hot-loop calls by caching results for at least 60 seconds. It also provides concrete example user queries with matching call arguments, which strongly guides an agent on when and how to invoke the tool.

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