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

Annotations already mark readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds meaningful behavior: parameters are processed remotely without application persistence, there are no independent finality checks, and it separates records by state. These details go beyond the schema and annotations.

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 zero filler. The core comparison is front-loaded, followed by usage guidance, exclusions, and input retrieval hints. Every sentence earns its place.

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?

Given the rich schema (100% parameter description, output schema, no nested objects) and strong annotations, the description covers the essential purpose, usage, and behavioral constraints. The phrase 'Retrieve reconcile with fetch or read its example resource to obtain exact inputs' is slightly cryptic but not a blocker. An agent can perform a local exception review with this definition.

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 coverage is 100% and both arrays are fully documented, so the baseline is 3. The description's mention of 'exact decimal totals' and retrieving exact inputs via fetch/example resource adds minor context, but it doesn't elaborate on how invoices and transfers relate beyond what the schema already states. No need for more.

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 verb and resources: 'compares your declared invoices with recorded stablecoin transfers.' It further separates payments by category (partial, pending, wrong-network) and names exact decimal totals, giving a precise scope. The 'No wallet sync, automatic matching, FX...' line helps distinguish it from sibling tools.

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?

'Use it for a local exception review before updating your books' clearly states the intended scenario. The long exclusion list provides when-not-to-use signals, such as no FX or tax accounting, though no sibling tool is explicitly named as the alternative. This is good context but slightly implied rather than fully explicit.

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