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

Annotations declare destructiveHint=true and idempotentHint=false, yet the description frames the operation as an inert sandbox that 'does not contact the receiver or verify an acknowledgment, availability or delivery' and merely 'returns an example health response.' A local HTTPS-prefix check destroys nothing, so the description directly contradicts the destructive annotation. This is an annotation contradiction, which caps this dimension at 1.

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 text is long and not front-loaded helpfully ('Unavailable historical backend. Sandbox/demo:' opens on an unrelated status note). Multiple boilerplate sentences about credentials, mandates, adapter authority, and proxy availability restate policy rather than tool behavior, and the redundant health-check/acknowledgment statements dilute the signal.

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 tool with no output schema, an open-world proxy POST, and an undocumented parameter, the description should resolve what the tool actually does and returns. Instead it is verbose, self-contradictory (contacts vs. does not contact the receiver), and leaves the request/response contract and the meaning of 'mode' unresolved.

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?

There is a single parameter (mode) with 0% schema description coverage, so the description carries the burden. Instead of explaining what 'mode' accepts, it defers with 'The existing product POST body. Supply its documented mode, arguments...' — pointing at documentation the agent does not have. The description adds no usable parameter meaning.

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 names a specific verb+resource (checks whether a callback URL starts with HTTPS, returns a health response), but it is undercut by two conflicting framings: 'It does not contact the receiver or verify an acknowledgment, availability or delivery' versus 'Check whether a callback receiver is alive, accepts proof payloads, and returns an acknowledgment shape.' The agent cannot tell whether the tool actually probes the receiver or just performs a local HTTPS-prefix check.

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?

'Validates callback receivers before paid work is delivered so proof can be sent, acknowledged, retried, and audited' supplies a when-to-use context. However, no alternatives are named among the many proof/rail siblings (e.g. wever_proof-inbox, wever_proof-relay), and no when-NOT-to-use is given. Usage is implied rather than prescribed.

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