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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals the two-step payment protocol (402 response, then x-payment header) and the outcome (signed PDR). While it doesn't detail side effects or auth requirements, the payment flow is well-explained. A minor gap is that it doesn't state whether the tool modifies state beyond creating the PDR.

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 two sentences long with a critical note front-loaded. It efficiently conveys the main purpose and the key restriction. Could be slightly more structured (e.g., separating purpose from usage caveat), but overall it is concise and scannable.

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?

The tool has an output schema (not shown) but the description only mentions 'signed PDR' without details on its format or contents. The complex payment workflow is adequately explained, but the lack of annotation and only partial output description leaves some gaps for an agent to fully understand the tool's behavior and response.

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 has 100% coverage per context signals, meaning all parameters are documented in the schema. The description only mentions work_hash in the context of the HTTP workflow, adding minimal extra semantics. It does not explain agent_sig or agent_pubkey beyond the schema defaults. Baseline 3 is appropriate as the description adds little value over the schema.

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?

Clearly states the action (notarize), resource (work artifact), and payment mechanism (x402 USDC on Base). The name and description differentiate from sibling notary_notarize by specifying 'paid'. However, the critical restriction 'DISCOVERY ONLY — cannot be called via MCP' is prominently noted, which slightly reduces clarity as it adds a usage constraint beyond the core purpose.

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?

Explicitly states that the tool is for discovery only and cannot be invoked via MCP, providing exact HTTP instructions (POST endpoints, headers) for actual use. This clearly tells the agent when NOT to use the tool and provides a precise alternative workflow.

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