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

Annotations already declare read-only and idempotent, but the description adds meaningful behavior: amounts are compared in integer cents to avoid floating-point errors, and the response includes a built-in proof that the listed differences re-add to the total gap. This goes well beyond the structured 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?

The description is well-structured: purpose, output lists, precision behavior, proof, and usage scenarios. It is a bit wordy, with the final metaphorical sentence being optional, but every sentence contributes useful information without redundancy.

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?

With a rich output schema and safe annotations, the description covers everything needed: what it does, when to use it, how it handles precision, and what the response proves. No critical context is missing for an agent to select and invoke the tool.

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 schema already provides complete descriptions for all six parameters (100% coverage). The tool description does not add additional parameter-level detail beyond the schema, so it relies on the schema's strong documentation. Baseline 3 is appropriate.

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 clearly states the tool reconciles two record sets, matches on key and amount columns, and returns three specific lists (only A, only B, difference). It also highlights the unique arithmetic proof, distinguishing it from generic diff tools like diff_tables.

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?

Explicit use cases are given: month-end close, platform payouts vs orders, and any 'these two numbers should agree' problem. It does not explicitly name alternative tools, but the context is clear and the VLOOKUP/groupby reference provides practical guidance.

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