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

With annotations supplied (readOnlyHint=false, destructiveHint=true, openWorldHint=true, idempotentHint=false), the description does add real context: signed mandates/grant requirements, no server credentials supplied, backend status surfaced, non-JSON backend errors. However, the 'sandbox/demo preview' framing sits awkwardly against destructiveHint=true and idempotentHint=false, blurring what actually mutates.

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?

Six-plus sentences with duplicated and conflicting claims ('unavailable historical backend' / 'sandbox demo preview' / 'create a ... record'), plus boilerplate disclaimers about catalog proxies and backend availability. The core action is buried rather than front-loaded.

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?

No output schema, a single undocumented parameter, and a large but self-contradictory description leave the agent without a reliable picture of what will happen on invocation. Behavioral disclaimer text is present, but the critical question — does this tool change state or only simulate — is never resolved.

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?

One parameter ('mode') with 0% schema description coverage, and the description adds no meaning beyond the object-level schema note to 'supply its documented mode, arguments, and required signed authority or grant.' Because coverage is very low, the description should compensate for the undocumented parameter but does not.

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 oscillates between incompatible framings: 'Unavailable historical backend' and 'Sandbox/demo: previews a release decision' versus 'Create a pending completion authority record that releases only when the required proof package exists.' An agent cannot tell whether this tool previews, records, or releases anything, and the name 'escrow-lite' is undercut by the explicit statement that it creates no enforceable escrow.

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?

'Operating boundary: Creates pay-when-proof-exists authority records for agent work' hints at context but gives no when-to-use/when-not guidance among the ~26 sibling rail/escrow/gateway tools. The only routing signal is generic credentials boilerplate, leaving the agent to guess whether this replaces or complements sibling tools like wever_delegated-authority or wever_payment-authority-inspector.

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