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

With no annotations, the description carries the full burden and does disclose several real traits: the return metric (discrepancies in basis points), the fail-closed behavior on incomplete evidence, and the cost (0.015 USDC). It omits some profile details (whether it is purely read-only, permission needs, or what qualifies as 'incomplete'), but the failure semantics and pricing are genuinely useful context.

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?

A single tightly-packed clause chain front-loads the core purpose, then appends behavior and cost. Every clause earns its place, with only mild density cost from compressing four distinct ideas into one sentence.

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?

An output schema exists, so the return value need not be re-explained, and the fail-closed note is valuable. But for a complex tool with 5 parameters, nested objects, and 0% schema coverage, the description leaves the parameter surface and required-input shapes largely undocumented, which is a real gap for correct invocation.

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 0%, so the description must compensate and it partially does: it maps declared_facts and observed_facts to the declaration/observation distinction and source_urls to 'independently fetched evidence'. However it never mentions asset or tolerance_bps, and the nested required keys (nav, reserve_ratio, as_of, unit) go unexplained.

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 uses a specific verb ('Compare') against clearly named resources ('declared NAV and reserve ratios' vs 'structured observed facts'), so the agent knows this is a reconciliation/attestation tool. It stands apart from generic siblings like verify or signed_result_comparator, though it does not explicitly name which sibling (e.g., rwa_asset_due_diligence, mandate_reserve) it replaces.

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 implies the inputs it needs (declared facts, observed facts, independently fetched evidence) but never states when to reach for it over sibling tools such as mandate_reserve or rwa_compliance, nor any prerequisites. No when-to-use or when-not-to-use guidance is present.

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