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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds genuinely new context: a 100-transaction-per-call cap, the fact that entries are 'suggested, non-binding' with the ledger platform owning amounts, cost basis, and posting, and a route-to-review flag. That framing prevents an agent from treating the output as authoritative postings, which is exactly the kind of trait annotations cannot express. It stops short of describing error handling or what happens for unmappable roles.

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?

Front-loaded with purpose, then output shape, then the parameter choice, which is the right ordering. It is dense but mostly earns its space; the enumerated tax citations (IRC §1001, §61, Rev. Rul. 2019-24, 2023-14) add credibility but are the one stretch that could be trimmed.

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 an output schema present, the return values needn't be spelled out, and the description still summarizes them; combined with the batch cap, the chart-of-accounts option, and the non-binding framing, an agent has everything needed to invoke this correctly in a classification-to-ledger pipeline.

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 already documented, including the per-role pattern matching and the omit-for-standard-chart behavior. The description largely restates that (account roles, omitting the chart, the 100 cap already in maxItems) rather than adding new semantic detail such as accepted 'type' values or matching fallback behavior.

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 states a specific verb and resource ('Map classified blockchain transactions into journal-entry-ready ledger lines against a chart of accounts') and explicitly scopes the input to already-classified transactions, which implicitly separates it from the sibling classifiers. An agent can tell what the tool produces (debit/credit lines, roll-ups) without opening the schema.

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 clear guidance for the optional parameter ('omit it for a standard crypto-treasury chart') and implies this runs downstream of classification, but never explicitly says when to use this versus classify_transaction or classify_batch, nor any exclusions or prerequisites. Usage is inferable but not stated.

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