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

Annotations already cover read-only, idempotent, non-destructive, so the bar is lower, and the description still adds real value: it discloses that invalid input never raises a protocol error but returns an {"error": ...} object, and that retry after correction is safe. It also explains balance semantics (running quantities per account and asset in time order, transfers' fiat values ignored), which is behavior no annotation conveys. Not a 5 only because error key coverage is summarized rather than enumerated exhaustively, though the example carries most of it.

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 the purpose and the FREE marker, then input/output shape, then ordering, then failure semantics — a sensible priority order with no filler sentences. The full example output is slightly long given an output schema exists, but it earns most of its space by illustrating issue and balance structure.

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 single-parameter validator with rich annotations and an output schema, nothing an agent needs is missing: it knows the input source, pipeline position, what the balances mean, and how errors surface. Return values are illustrated only as far as needed, since the output schema carries the rest.

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?

Only one parameter and the schema covers it at 100%, so the baseline is already a 3. The description goes beyond the schema by sourcing the rows ('<rows from parse_transactions>'), telling the agent where the input comes from, and showing a concrete input example.

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 — 'Find the problems that break a lot build: missing values, duplicates, negative balances' — and immediately delimits scope against siblings ('Not a tax check'). An agent can distinguish this from build_lots, match_transfers, or wash_window_check without opening any 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?

Gives explicit ordering in the pipeline ('Use after parse_transactions and before build_lots') and an explicit exclusion ('Not a tax check: it checks the ledger's arithmetic consistency only'). Both when-to-use and when-not-to-use are present, with the predecessor named.

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