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

The description goes beyond the minimal annotations by revealing the internal dedupe-first step, the SuperCat prediction criteria, and the distinction between auto-applied and confirmation-only outcomes. It does not explicitly enumerate every side effect (e.g., updating expense records), but 'auto-applied' and the readOnlyHint=false annotation convey that writes occur.

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 description is two sentences and front-loads the main purpose before giving precise thresholds. Every clause carries useful information, and no redundant or filler wording is present.

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 tool with no input schema, the description gives enough procedural context: dedupe first, predict with SuperCat, apply only if strong, otherwise surface for confirmation. It does not describe the return format or confirmation UI, but the essential behavior is sufficiently covered.

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?

The input schema is empty, so the baseline of 4 applies; the description does not need to explain parameters that do not exist. It indirectly clarifies that the tool operates over the current set of supplier-less expenses in the environment.

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 action—'Attribute every supplier-less expense to a supplier'—and distinguishes the tool by detailing the dedupe-then-predict workflow and auto-apply versus confirmation behavior. This makes it clear how match_suppliers differs from siblings like suggest_suppliers or dedupe_records.

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 explicitly states the target scenario (supplier-less expenses) and provides concrete thresholds for when predictions are auto-applied versus surfaced for confirmation. It does not name alternative sibling tools, but the context and criteria make intended usage clear.

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