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

The description goes beyond the readOnlyHint/idempotentHint annotations by spelling out that it does not change page or account state, does not access customer data, and does not provide personalized financial advice. This gives an agent clear side-effect and privacy expectations.

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?

Two tight sentences front-load the core function and then state behavioral boundaries; every clause adds information. There is no filler or repetition.

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 a full input schema, an output schema, and rich annotations, the description covers the relevant behavioral boundaries and use context. Nothing necessary for correct invocation—safety, data privacy, or input scope—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?

Schema description coverage is 100%, so the parameters are already fully documented with ranges, defaults, and enums. The description only topically lists inputs like 'principal, monthly contributions, annual return, years' without adding syntax or behavioral 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 identifies a concrete function ('Calculates compound interest') and enumerates the exact inputs and compounding frequencies, making its scope unmistakable among siblings like calc_investment_return or calc_savings_goal. The 'Read-only educational calculator' label adds context that this is a projection tool, not a transactional one.

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 implies use whenever a compound-interest projection is needed and explicitly excludes personalized advice, but it does not name an alternative tool or state when not to use it. Agents must infer selection from the domain rather than receive explicit routing guidance.

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