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

Well beyond the annotations, the description discloses that the scenario is inert — no invoice, payment, order or approved budget is touched — and it documents the two-phase confirmation protocol in full: status='confirmation_required', an action_id and plan_token, with the write only occurring after confirm_action. That is exactly the behavioral context an agent needs to not misread this as a direct write, and it is consistent with destructiveHint=false.

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?

Front-loaded with purpose and instantly followed by the sandbox guarantee, then modeling semantics, then a clearly labelled CONFIRMATION block — a sensible ordering. The four illustrative percentages are slightly padded, but they do real work in teaching the assumption format, so nothing is truly wasted.

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 mutation tool with nested assumptions and no output schema, the description covers the risky parts: side effects, confirmation flow, and how to encode target/operation/value. The remaining gaps (period selection, horizon_months, the label/currency fields on each assumption) are handled by schema descriptions, so an agent can call it correctly, but a sentence on the created scenario's identifier or how to chain into fin_scenario_compare would close the loop.

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?

At 60% schema coverage the description earns credit for adding meaning the schema does not: the target vocabulary is grounded in examples ('sales minus 20%' → income, 'suppliers plus 8%' → spend, payroll plus 5%), and the sign convention ('a decrease is a negative value rather than a separate operation') is a genuine constraint absent from the schema. It says nothing about name uniqueness, period, horizon_months or currency, which are left to 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 opens with a specific verb+resource ('Create a what-if scenario with its assumptions') and immediately concrete examples of what an assumption looks like. It goes on to define the conceptual scope (a sandbox that changes nothing and exists to be compared), which lets an agent distinguish this from the other finance siblings without opening a 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?

It gives clear context for when this tool applies (building hypotheticals for income, spend or payroll) and explains the modeling vocabulary the agent needs — targets, the three operations, and that decreases are negative values rather than a separate operation. It stops short of naming alternatives or exclusions (e.g. vs. forecast variance or break-even), so the routing decision is implied by 'its only effect is that it can then be compared' rather than stated.

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