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

Annotations only give the coarse profile (not read-only, open-world, not idempotent, not destructive). The description adds genuinely useful context beyond that: it grants no authority, never supplies credentials, performs no provider work/callbacks/document retrieval/attestations, and includes the x402/Base USDC payment terms. This is real behavioral disclosure, though the 'bounded computation on caller-supplied data' claim sits uneasily with openWorldHint=true.

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-loading is poor: the first sentence is pricing and 402/x402 mechanics rather than purpose. The prose is repetitive ('bounded computation on caller-supplied data' appears twice), mixes legal disclaimers with operational detail, and includes boundary statements with no operational use for the caller.

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?

Payment, authority, and credential boundaries are reasonably well covered for a tool with no output schema, and the 'prepare, not submit' framing is useful. But an agent still cannot tell what artifact is returned or what the evidence arrays must contain, which are essential for a validation-oriented task.

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 0% for the four required properties, so the description carries the full burden and largely fails it. Only 'Connect recipient' loosely gestures at recipient_id and 'DiligenceOps task' at the constrained service_id; the critical distinction between available_evidence and expected_evidence is never explained.

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 does contain a specific verb+resource: 'Prepare a validated DiligenceOps task for a specific Connect recipient,' which tells an agent what the tool produces. However, this is buried in payment boilerplate and gives no differentiation from the numerous pricing/rail siblings (e.g. wever_agent-work-order-exchange, wever_agent-decision-packet-rail).

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 usage as a preparation step ('Submission, recipient permission and execution remain separate steps') and lists prerequisites ('Existing product credentials, signed mandates, and single-use action grants remain required where applicable'). But it never states when to choose this tool over the ~27 sibling rails or when not to use it.

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