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

Annotations already declare readOnlyHint and destructiveHint false, so there is no contradiction. The description adds useful behavioral context: it 'returns an optimal settlement plan', 'No settlement is executed', and 'Free', explaining the safe, non-executing nature of the call beyond what annotations 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 front-loaded with the purpose, uses a compact example, and has no filler. Each clause (input, output, safety, usage sequence, cost) earns its place.

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?

For a read-only planning tool with no output schema, the description explains the return plan elements (settle-vs-hold, stablecoin, fee), the input format, and the intended position in the workflow before card.settle. It is sufficient for an agent to select and invoke the tool correctly given the annotations and schema.

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 already covers both parameters at 100%, including an inline example for positions and a default note for settlementDate. The description's 'net positions per corridor' and currency examples reinforce the concept but do not add new parameter-level meaning beyond the schema.

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 says 'Plan treasury settlement for a crypto card program' with explicit input (net positions per corridor) and output (optimal settlement plan with corridors, stablecoin, fee). The phrase 'Call this before card.settle' and 'No settlement is executed' clearly distinguishes it from settlement execution tools.

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?

It states 'Call this before card.settle to review the plan', giving direct when-to-use guidance. It lists what the tool returns and explicitly says 'No settlement is executed', signaling when not to use it (when execution is desired). It also mentions 'Free', which may help tool selection.

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