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

Annotations already declare readOnly, idempotent, and non-destructive, and the description adds meaningful detail: amounts are compared in integer cents to avoid floating-point phantom differences, and the response proves correctness by re-adding differences to equal the total gap. This goes well beyond the 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 four sentences, each earning its place: function, precision handling, proof mechanism, and usage scenarios. It is front-loaded with the action verb and remains free of filler.

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?

The tool has an output schema and strong annotations, and the description covers all necessary context: what it does, how it handles numeric precision, what the output looks like (three lists plus proof), and when to use it. No important behavioral aspect is missing.

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 covers all 6 parameters, so the baseline is 3. The description adds semantic context by explaining that 'key' is the column to match on, 'amount' is the column to compare, and url_a/url_b/text_a/text_b represent the two sides (e.g., books vs statement). This reinforces the schema descriptions and gives real-world meaning.

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 'Reconciles two sets of records' and specifies exactly what happens: matching rows on a key column, comparing an amount column, and returning three named lists. It clearly distinguishes from sibling diff tools by emphasizing the arithmetic proof element.

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 concrete use cases ('month-end close, platform payouts vs orders, or any "these two numbers should agree and do not" problem') and frames it as the automated replacement for manual VLOOKUP/groupby. However, it does not explicitly name sibling tools as alternatives or list when not to use it, so it stops short of a 5.

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