Reconcile a total

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

Annotations already declare readOnly, idempotent, non-destructive; the description adds substantive behavior beyond them: formulas are not evaluated, and only usable cached results are labeled and counted. That caveat materially affects how an agent interprets a mismatch, which is exactly the value beyond structured fields.

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?

Two tight sentences: the core operation first, the caveat second. No filler and nothing important buried.

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?

An output schema exists, so return-value explanation is not needed, and annotations cover safety. The description supplies the key caveat about cached vs. formula values; only minor items (e.g., behavior when the column is missing or non-numeric) are left implicit.

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 every parameter is documented in the schema, including the tolerance default and decimal-string format. The description only echoes the concepts of control total and tolerance without adding format or edge-case guidance, so baseline 3 applies.

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?

States a specific verb chain and resource: sum a selected column and compare against a supplied control total within a tolerance. An agent can distinguish this from compare_workbooks or check_formula_integrity, though it doesn't explicitly name those siblings.

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?

The description implies the use case (verifying a column total against an expected value) but gives no explicit when-to-use/when-not guidance or routing versus the sibling integrity/compare tools. The 'formulas are not calculated' clause hints at a limitation rather than selecting among alternatives.

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