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

Goes well beyond the readOnly/destructive annotations: it discloses what is preserved (invoice history, other-currency budgets), the permission requirement, the five-minute token lifetime, and that the change is not applied. This is exactly the kind of behavioral context annotations cannot convey.

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?

Three tight sentences, front-loaded with scope, then side effects, then return behavior. No filler and every clause carries operational meaning.

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 no output schema, the description supplies the return shape (exact preview plus confirmation token) and side-effect guarantees. The only minor gap is not spelling out how the token is redeemed, leaving the agent to infer the delete_budget handoff.

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 0%, so the description must compensate. It clarifies that the budget is keyed by category and currency ('the exact category/currency budget'), which matches the nested BudgetKey, but adds no format details (e.g. currency as a 3-letter code) beyond the schema's maxLength constraints.

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 ('Prepare removing') and a precisely scoped resource ('only the exact category/currency budget'), and explicitly frames it as a preview rather than an application. An agent can immediately tell this apart from delete_budget and from budget-creation siblings.

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?

Explains the workflow context: requires settings permission and confirmation, and returns a confirmation token instead of applying the change. It stops short of naming the follow-up tool (delete_budget) that consumes the token, so the routing guidance is clear but not fully closed.

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