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

Annotations only cover readOnlyHint=false and openWorldHint=true. The description goes far beyond by disclosing the cost model (250 sats via L402), batching behavior (100 calls for 25000 sats), the HTTP 402 payment flow with retry instructions, randomized commitment submission, pending_calendar return, and failure behavior when calendars are unavailable. This is rich behavioral context not derivable from annotations.

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 structured with clear headers (PURPOSE & BOUNDARIES, USAGE GUIDELINES, BEHAVIOR & CONSEQUENCES), which aids navigation. However, the L402 payment details are verbose and some information (e.g., 'Live L402 Satoshi settlement: a configured NWC wallet issues the exact-priced Lightning invoice') is highly detailed and could be more concise for a tool description. The length is justified by complex payment flow, but the density of payment-specific jargon reduces readability.

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?

Given the tool is a write operation with payment flow, no output schema needed for return values (though one exists), and the description covers purpose, usage, payment mechanics, failure modes, and boundaries. It is thorough for a notarization tool with L402 integration.

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 input schema already has 100% description coverage, so the baseline is 3. The description adds value by specifying 'exactly one 64-character hexadecimal hash' and clarifying the otsProofHex decoding requirement, which supplements the schema's parameter documentation. The addition is marginal but meaningful.

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 states a specific verb (Create) and resource (detached OpenTimestamps .ots receipt) and explicitly draws boundaries against sibling tool proof.verify ('not a replacement for proof.verify'), enabling precise sibling discrimination.

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 provides explicit when-to-use guidance ('Submit exactly one 64-character hexadecimal hash'), when-not-to-use ('Do NOT use this as evidence of immediate Bitcoin confirmation or as a replacement for proof.verify'), and names the alternative tool. The usage conditions are unambiguous.

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