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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds important context beyond those: it is offline, calls no model or payment, performs no live requests, and processes parameters remotely without application persistence. This is exactly the kind of behavioral disclosure an agent needs to avoid misusing the tool.

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 main function is front-loaded and clear, but there is redundancy: 'It is an offline planning tool; no model or payment is called' is immediately followed by 'Offline planning only. No live requests, model judge, payment, dynamic bandit or production routing.' This repeats the offline and payment exclusions without adding new information. Otherwise, the description is compact.

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 an output schema present, full parameter schema, and strong annotations, the description does not need to explain return values. It covers offline behavior, non-persistence, and how to obtain exact inputs via fetch or an example resource, giving an agent sufficient context to call the tool correctly.

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?

Schema description coverage is 100%, so the baseline is 3. The description adds relational meaning by framing cost, success, and latency as assumptions, explaining that budget is checked against the worst-case total, and stating that feasible options are sorted by expected cost. This helps the agent understand how the parameters interact beyond their individual schema descriptions.

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?

States a specific verb and resource: 'compares short supplier sequences' using cost, success, and latency assumptions, then checks worst-case total against budget and sorts feasible options by expected cost. It also differentiates itself from siblings by explicitly declaring it is an offline planning tool and excluding live requests, model judge, payment, dynamic bandit, and production routing.

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 explicitly scopes use to offline planning and enumerates exclusions: no live requests, model judge, payment, dynamic bandit, or production routing. It also names an alternative path for obtaining inputs: 'Retrieve route with fetch or read its example resource,' giving an agent clear when-to-use and when-not-to-use guidance.

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