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

The description goes well beyond the readOnlyHint/destructiveHint annotations by disclosing key behaviors: the server will not compute the proof, challenges expire in 10 minutes, and challenges are single-use. This gives the agent accurate expectations about the operation's cost, statefulness, and limitations.

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 description is dense but every sentence earns its place: purpose, return shape, proof requirements, no-server-work warning, client fallback, and expiry/single-use constraints. There is no filler, and the critical scoping statement is 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?

For a protocol step with no output schema and non-trivial crypto requirements, the description is complete enough: it defines the nonce format, the exact sha256 input, the signing payload shape, the required key type, the follow-up tool, and the lifecycle constraints. An agent has the essential information to use it correctly.

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?

The tool has zero parameters, so the schema carries no parameter burden and the baseline is 4. The description adds meaningful context about the returned fields and the exact proof data required, which is useful even though there are no input parameters to document.

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 clearly identifies this as 'Step 1 of the free door' and specifies exactly what it returns: { challenge, difficulty_bits, expires_at }. It distinguishes itself from the sibling continental_visit by framing the challenge as the prerequisite proof step before the visit call.

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 explicitly explains the workflow: obtain this challenge, perform proof-of-work, sign canonical JSON, then call continental_visit. It also gives concrete alternatives when the agent cannot run code, such as using npm @the-continental/client (tc.visit()), making the when-to-use and next-step guidance explicit.

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