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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds substantial context beyond them: no network upload, no API key, row-by-row running-balance walk, and a specific output claim ('reports rows ... each with a likely fix') plus parity with `docfig check --json`. Nothing here contradicts 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?

Two compact sentences: the purpose and error list come first, then the input contract and the CLI-equivalence note. Every clause carries information; nothing is padding.

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 8 optional parameters and no output schema, the description carries the return-value burden itself by naming what the report contains (offending rows plus likely fixes) and by pinning down both input formats and offline behavior. An agent has everything needed to call it correctly.

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%, so the baseline is 3, but the description adds the either/or relationship between the two input parameters and reiterates that the first row is the header, which is the highest-risk mis-input. It does not clarify opening/closing_balance usage beyond what the schema already states.

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 resource ('Check a bank or credit card statement's transactions table for errors') and enumerates the exact defect classes it detects, so the agent knows precisely what the tool does. It never names the siblings (convert_statement, combine_statements) to differentiate, which keeps it just short of a 5.

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 gives concrete invocation context — 'Free and offline: no API key, nothing is uploaded' — and explains the two accepted input modes ('Give the table as csv_text ... or as rows'). However, it offers no when-not-to-use guidance or routing to the convert/combine siblings.

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