balance_reprocess

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that it 'Re-parses the PDF file and updates the account rows,' which reveals the destructive/updating nature. However, it doesn't clarify whether the reprocessing overwrites existing rows, whether it's reversible, what happens to previously manually-edited rows, or what the return value looks like. Half of the burden is met.

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 sentences, zero wasted words. States what it does, the mechanism, and the use case. Efficient and front-loaded.

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?

For a reprocessing/mutation tool with no output schema and no annotations, the description provides a basic understanding of purpose and use-case trigger. However, it lacks detail on side effects, data loss risk, permissions needed, or what happens to previously extracted/modified data. The complexity is moderate (a reprocessing action on financial data), and given the absence of annotations, more behavioral context would help.

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%, so both parameters are documented with descriptions ('Trial balance UUID to reprocess' and 'Company UUID (overrides STORNO_COMPANY_ID env var)'). The description adds the context that companyId overrides an environment variable, which is useful. However, the parameter descriptions are relatively minimal and the tool description itself doesn't elaborate on parameter usage beyond the schema. 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 'Reprocess a trial balance PDF. Re-parses the PDF file and updates the account rows.' This uses a specific verb (reprocess/re-parse) and resource (trial balance PDF). It distinguishes from siblings like balance_list and balance_rows by focusing on the parsing/reprocessing action, though it doesn't explicitly name sibling alternatives.

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 states it's 'Useful after parser improvements,' which implies the context where it should be used (after a parser update to re-extract data). However, it doesn't explicitly state when NOT to use it or name alternative tools. The guidance is implied rather than explicit.

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