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

Annotations already declare read-only, idempotent, non-destructive, but the description adds substantial context beyond them: results are computed from real GL rows rather than asserted, `solvent` requires both full reserve and zero unbalanced entries, single-sided rows are flagged as defects even when coverage holds, and absolute dollar amounts are deliberately withheld. That is rich disclosure of semantics the annotations cannot convey.

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 core question and the return contract, and most sentences carry information. It loses a little to redundancy — the CO 472 no-absolute-amounts exclusion is stated twice and the return property list appears in both prose and a `Returns:` line — plus opaque internal codes (CO 192, CO 385, CO 466) that add little for an outside agent.

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 no output schema, the description enumerates the returned properties, their meaning, and the shape of `solvent`; it also explains what is intentionally omitted. An agent has everything needed to call it and interpret the result.

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?

The tool takes no parameters, so the schema baseline is 4 and there is nothing to document. The description reinforces this with an explicit empty-arguments example, leaving no ambiguity about invocation.

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 question and resource: returns the dollar ledger's live solvency invariant as named properties (`solvent`, `fully_reserved`, `coverage_ratio`, `unbalancedEntries`, `audit`). An agent can tell this apart from siblings like federation_latency or federation_pricesheet, which it references only as behavioral analogues rather than duplicating.

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?

Frames the tool's context clearly — 'checking whether the backing exists is discovery', public, read-only, always free — which tells the agent when it is appropriate. It does not name a competing tool or an explicit when-not condition, so it stops short of full routing guidance.

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