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

Adds behavior beyond the annotations: zero blocks future spending, and refunds do not restore the already-consumed daily limit — a genuinely non-obvious semantic. It also clarifies the authorization boundary. It does not, however, state that existing limits are overwritten by the call, despite destructiveHint=false and idempotentHint=false leaving that ambiguous.

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 dense sentences with the resource, unit, and zero-state semantics front-loaded; the prerequisite and non-scope caveats follow. No filler or restatement of the title.

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 two-parameter mutation with no output schema, the description covers units, effects, preconditions, and exclusions. It omits what the call returns and whether both limits are applied atomically, which an agent might want before relying on the result.

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 carries the burden — and it does map both parameters to their meaning (per purchase and per UTC day, in integer EUR cents). The 1,000,000 upper bound and 0 minimum remain schema-only, and there's no guidance on interaction between the two values.

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 (change spending limits) scoped to 'this authenticated sandbox machine', and specifies the unit of measure (integer EUR cents per purchase and per UTC day). An agent can immediately tell this apart from sibling read tools like get_wallet or payment-flow tools like purchase/create_card_authorization.

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?

Explicitly directs the agent to call get_wallet first to inspect current limits, giving a clear call ordering. It also delimits scope ('does not authorize another person's card or make a purchase'), though it does not contrast against other mutation siblings such as fund_wallet or revoke_card_authorization.

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