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

With annotations present (openWorldHint=true, idempotentHint=true, destructiveHint=false), the description still adds real context beyond them: that results are historical flow rather than level, that "never-asked-this-size" is neither a refusal nor a failure, that unread vaults are counted separately as population, and that nothing is a forecast. It does not explain cost/billing mechanics behind the "(paid)" label or rate limits, which keeps it out of the top band. Note the mild tension between the plainly read-only framing and readOnlyHint=false, but no explicit contradiction.

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?

It is well front-loaded — the trigger condition leads — but it is heavily overwritten for a two-parameter tool: all-caps rhetorical emphasis, the "LEVEL vs FLOW" aside, and the auditor anecdote consume space that a tighter statement of the three verdicts would cover. The anecdote and the verdict definitions do earn their place; the emphatic repetition does not.

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 screen with an output schema and full schema coverage, the description supplies everything an agent additionally needs: the meaning of each verdict, the caveat that absence of history is untested rather than safe, the population counter, and the historical-not-predictive framing. Nothing required to call or interpret it correctly is missing.

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 the schema already documents amountUsd (including the 6000000 example and why it is required) and the limit/count relationship. The description reinforces the meaning of amountUsd but adds no syntax, format, or edge-case guidance beyond the schema, so baseline 3 applies; `limit` is not touched on in the description at all.

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 concrete job — screen every vault that has withdrawal history for whether a withdrawal of the given size has actually cleared — and explicitly contrasts it with siblings: "Every other exit reading here is about one vault; this asks the same question across every vault" (i.e. vault_exits / vault_exit_confidence). The three verdict tokens pin down exactly what the tool returns, so an agent can distinguish it from neighboring exit tools without opening a 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 a clear triggering condition ("YOU HAVE A SIZE AND YOU WANT TO KNOW WHERE IT HAS ACTUALLY CLEARED") and implicitly positions itself against the single-vault exit readings. However, it never names the alternative tools an agent should use for a single vault or for a forecast-style check, so the routing guidance stays inferential rather than explicit.

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