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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, but the description adds genuinely new behavioral facts: references and supplied hashes remain unverified, no destination is contacted, nothing is persisted, and existing credentials/signed grants are still required. The 'supplied hashes remain unverified' disclosure is important context an agent cannot derive from the annotations alone.

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?

The purpose is front-loaded, but the body repeats the same disclaimer multiple times ('No authority, payment, execution... delivery or persistence' then 'no destination is contacted... nothing is delivered or persisted'). Roughly half the text is redundant boundary boilerplate that does not advance understanding.

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 complex nested schema with no output schema and 0% parameter coverage, the description covers behavioral boundaries exhaustively but under-serves the parameter and return-shape side. It conveys the general output (a prepared envelope plus binding digest) without detailing the destination kinds or reference envelope structure the agent must construct.

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% across four required parameters, so the description must carry the burden, but it only loosely gestures at concepts ('reference envelope', 'source/destination binding digest', 'references and supplied hashes'). It never explains the mode const, the agent-vs-callback destination oneOf, or the maxItems/reference format constraints, leaving the nested schema largely undecoded.

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 set: 'Prepare a reference envelope and deterministic source/destination binding digest.' An agent understands it produces an envelope plus a binding digest. It does not differentiate itself from related siblings such as wever_proof-inbox or wever_receipt-passport, so it falls short of a 5.

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?

Usage is implied through the operating boundary ('Prepared computation on caller-supplied data only') — the tool is a preparation step, not a delivery step, and takes caller-supplied data. However, no alternative tool is named and no explicit condition ('use this when...') is given, leaving the agent to infer routing among the many wever_ siblings.

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