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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the safety profile is mostly carried structurally. The description adds one genuinely useful fact beyond that — 'The bill stays on the record' — clarifying rejection is not a deletion. However, 'Effects: bill rejected.' is a tautology, and it never says whether a rejection can be undone, re-approved, or what the bill's subsequent state is.

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 the caller condition are front-loaded, which is good. But the closing 'Effects: bill rejected.' restates the first clause verbatim and earns nothing, and the staccato fragments cost more space than they return.

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, no-output-schema mutation with annotations present, the description covers what the tool does, when to fire it, and that the bill persists. It is missing the downstream picture an agent would want before an irreversible-sounding vendor decision: reversibility, effect on payables/aging, and whether the bill can later be approved.

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 both bill_id and reason are already documented in the schema, giving a baseline of 3. The description reinforces that a reason is mandatory ('With a reason') but contributes no format, length, or vocabulary guidance beyond what the schema states.

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 gives a specific verb ('record that a bill will not be paid') and names the resource, plus concrete reasons (wrong, disputed, duplicate, not theirs) that let an agent distinguish this from purch_approve_bill or purch_record_bill_payment. It never names a sibling outright, so differentiation is inferred rather than stated.

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 offers a real usage condition — 'do it when the person says so, with their reason' — which is better than nothing and captures the human-in-the-loop trigger. But there are no exclusions and no alternatives cited, so an agent facing a disputed bill has no guidance on whether to reject, match/dispute, or issue a credit instead.

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