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

The most important behavioral fact — the call is refused to the agent regardless of role, because loosening tolerance is a human judgment about vendor overcharge — is disclosed up front and is not derivable from the annotations. It also states the default (0) and the effect, and nothing contradicts readOnlyHint=false or 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?

The front-loaded definition and effects line are efficient, but the human-only refusal is stated twice in near-identical wording ('this act is refused to you whatever your role' and 'Refused to you whatever your role'), which wastes space even though the repetition reflects deliberate emphasis.

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 three-parameter config setter with no output schema and full annotation coverage, the definition supplies what an agent needs: what the setting means, its default, the refusal policy and the escalation path. Return-shape detail is unnecessary since no output schema exists and the effect is stated.

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?

With 100% schema coverage the schema already documents reason, qty_pct and price_pct thoroughly. The description adds the useful default value ('0 by default') and the joint framing of the two percentages, but offers no additional format or edge-case guidance beyond 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 defines the resource precisely (price percentage and quantity percentage a bill may stray from its order before approval fails) and the closing 'Effects: match tolerance set.' confirms it is the setter for that tolerance. It never states the verb itself in the body — the name carries it — but the resource is unambiguous and no sibling tool touches match tolerance.

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 states explicitly that the act is refused to the agent whatever its role, instructs it to ask a human, and names the alternative workflow (show the numbers via p2p_bill_match so the person decides). When-to-use, when-not-to-use and the alternative are all spelled out.

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