Agent Verifier — Independent Number Verification

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

With no annotations, the description carries the full burden and mostly does: it discloses the return payload ('every mismatched cell with the recomputed value and the difference, plus a signed verification receipt (verification ID, UTC time, SHA-256 content hash)') and two hard limits (arithmetic only, no source-data validation). It stops short of stating that content is not mutated or whether any permissions/quotas apply, which is the only remaining gap for a zero-annotation tool.

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?

Four sentences, front-loaded with the core action, then usage trigger, then return shape, then limits — each sentence contributes distinct information with no restatement of the title or schema. Dense but never padded.

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?

No output schema exists, so describing the mismatch list and the signed receipt is necessary and is done here. Combined with the stated scope limits and the input format expectations, an agent has everything needed to decide to call it and to interpret the result.

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 description coverage is 100% and the single parameter's schema text already names markdown/CSV/TSV and the 'name: value' breakdown form. The description repeats those formats and adds only domain flavor (invoice, quotation, budget) without clarifying edge cases such as how totals must be labeled for detection to work, 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 and resource ('Verify that the numbers in a finished table add up') and pins down scope: row totals, column totals, subtotals, line-item sums. It also explicitly separates itself from a calculator ('does not evaluate expressions; it audits finished numbers'), so the agent knows exactly what class of tool this is.

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?

Gives a concrete triggering condition ('Use this when you have produced or received a table, spreadsheet, CSV/TSV or markdown table, a cost breakdown, invoice, quotation or budget') plus exclusions ('Checks arithmetic consistency only; does not verify source data'). No siblings exist, and the when/when-not framing is explicit enough that no inference is needed.

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