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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety and idempotency are covered. The description goes further, adding valuable behavioral disclosure: the EMI stays constant, the loan shortens, and the return shape switches to { schedule, payoff_month, total_interest_paid, total_prepaid, interest_saved } when prepayments are supplied. It also warns that start_month is loan-relative here versus plan-absolute on persisted loans, which prevents a real off-by-basis error.

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 purpose and return behavior are front-loaded, which is good, but the prepayment parenthetical crams ambiguity resolution for frequency, start_month, and step_pct into one long sentence. The comment about loan-relative vs plan-absolute months is useful but reads as a footnote bolted onto the end, making the paragraph denser than it needs to be.

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?

There is no output schema, so the description must explain return values, and it does: a plain array normally, or a richer object with payoff_month, total_interest_paid, total_prepaid, and interest_saved when prepayments are given. It also discloses the loan-relative month basis. What is missing is any statement about required inputs or error behavior, but for a pure deterministic calculator with no annotations gap, this is nearly complete.

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 coverage is 100%, so the schema already documents every field, including start_month, frequency, and step_pct. The description re-explains the prepayment shape and clarifies that null frequency means a one-time lump and step_pct is a growth percentage per recurrence, which adds meaning beyond the schema but does not add much that the schema lacks. Baseline 3 applies when the schema carries the load.

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 ('Pure calculation of EMI and a month-by-month amortization schedule for a loan') and distinguishes itself from the siblings, which are projections, refinancing, and plan simulation rather than a deterministic EMI calculation. An agent can classify this as a pure calculation vs a stateful planning operation without opening the schema.

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?

Implies usage via 'Pure calculation' and the contrast with persisted loans, but it never states when to choose this tool over siblings such as loan_refinance or simulate_plan, nor when prepayment modeling should be used instead of the plain schedule. Adequate context with a clear gap in call routing.

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