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

Major behavioral traits are disclosed beyond annotations: the response may be exact or a min/max range depending on channel/outcome, it 'does not promise an accuracy percentage - check cost_range,' and the cost is free with ~100ms latency. These details inform the agent's expectations and are not visible in the annotations or schema.

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 organized into clear sections (summary, examples, when to use, when not to use, cost, latency) with no filler. Every sentence contributes decision-relevant information, and the core purpose is front-loaded in the first sentence.

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?

Given there is no output schema, the description explains what the response will contain (cost, latency, success-probability, exact vs range, cost_range field). It also covers usage constraints, caching, cost, and latency, so an agent has enough information to invoke the tool correctly without needing additional context.

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 only describes 'params' and leaves 'operation' undocumented (50% coverage). The description compensates with two concrete call examples showing the shape: preview_cost({"operation": "send_message", "params": {"preferred_channel": "sms"}}). It adds meaningful context for both parameters, though it does not explicitly define 'operation' in prose.

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 opens with a specific verb and resource: 'Return an expected cost estimate, latency estimate, and success-probability estimate for a proposed call before execution.' It clearly differentiates from siblings by being the only tool about cost preview, and it provides concrete example queries that demonstrate the intended use.

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?

Explicit WHEN TO USE guidance ('Use before any operation when the agent is operating under a budget constraint and needs to decide whether to proceed') and WHEN NOT TO USE guidance ('Do not use in a hot loop — cache the result for at least 60 seconds') are both present. Although no alternative sibling is named, none of the siblings serve a similar purpose, so this is complete.

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