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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes further: it specifies the matching predicate (same asset, different account, deposit inside window, quantity within tolerance_pct of amount net of fee) and a full error contract — no protocol errors, an {"error": ...} object, and retry safety after correction. That is meaningful context an agent cannot get from structured fields.

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 a worked example, matching criteria, intended ordering, exclusions, and error behavior — a sensible progression. It is dense and borderline long (the inline example is verbose), but no sentence is wasted and the 'FREE' note is the only soft addition.

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 3-parameter matching tool with an output schema, the description supplies everything else an agent needs: input shape, match semantics, sequencing relative to build_lots, out-of-scope cases, and error/retry behavior. Return-shape explanation is technically redundant with the output schema but harmless.

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 earns extra credit by explaining what the parameters mean operationally: tolerance is compared against the amount sent net of fee, and the window is measured after the withdrawal. The example input concretizes ledger and window_minutes usage.

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 — 'Pair withdrawals with the deposits that received them between your own accounts' — and immediately bounds scope to transfers among the user's own accounts. Sibling differentiation is explicit via build_lots and the exclusion of third-party transfers.

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 an explicit ordering instruction ('Use before build_lots so basis and holding period move with the coins instead of being treated as a sale') and an explicit exclusion ('Not for transfers to third parties: those stay unmatched and should be typed gift_out or sell'). There is nothing left to infer about when to reach for this tool.

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