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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with a precise non-action list ('no network request, fetch, money movement, message, sharing, configuration change or external write'). Beyond that it discloses cost (0.10 USDC per call on Base via x402 exact), the free-call allowance, the auth requirement (X-Wever-Wallet-Proof bound to exact JSON arguments and route), and the return form (Ed25519 signed receipt). This is substantial context annotations cannot carry.

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 core action is front-loaded after the 'Agent Control:' prefix and the closing operational facts (pricing, signing, contract link) are short and scannable. It loses a little to redundancy, since the same conditions (shared credential, predictable credential, unauthenticated reachable endpoint, bulk with no rate limit) are listed once as inputs and again as findings, and to one long semicolon-chained 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?

There is no output schema, and the description compensates by naming the report contents, the three possible verdicts, and the signed-receipt delivery mechanism. Combined with auth and payment mechanics, an agent has everything needed to call this correctly 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?

Schema coverage is 75%, so the schema already does much of the work, but the description adds interpretive meaning for the nested groups — 'who holds each, whether production accepts it, whether it is predictable' for credentials, and 'reach from the sandbox, internet exposure, accepted credentials, bulk access, rate limit' for endpoints. That directly maps caller intent onto the nested fields rather than just restating their names.

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 opens with a concrete verb and resource ('submit an environment-separation design') and enumerates exactly what the submission covers: credentials, endpoints, egress default. It also explicitly routes the adjacent question elsewhere ('What an agent may do inside its environment is wever_authority-scope-check'), so an agent can separate this tool from its closest sibling without reading the schema.

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 context is clear: this is for auditing whether a sandbox can reach a production effect, and the named alternative covers in-environment permissions. It also tells the caller what the verdict values mean (escape_path_open, separation_unverified, contained), which helps interpret the result. It stops short of an explicit 'use this when / do not use this when' statement for the sibling.

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