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

Annotations only say non-read-only and non-destructive; the description adds the materially important fact that USDC locks at intent creation (a financial commitment, not a safe retryable write) and documents the `bootstrap_required` structured error with the exact remediation and retry flow. That is behavior an agent cannot infer from the schema or 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?

Three sentences, no filler: purpose and class enumeration first, the money-lock consequence second, the error/retry path last. Each sentence carries distinct, actionable information.

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 10-parameter, 7-required mutation with a nested object and no output schema, the description covers the critical unknowns: what gets locked, the class semantics, and the pubkey bootstrap dependency. It does not describe the post-creation flow (intent id, next step like `claim_intent`/`discover_intents`) or how a partial failure behaves, which would complete the picture.

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 description coverage is 100%, so all ten parameters including `predicateParams` and `buyerStakeUsdc` are already documented in structured fields. The description adds only the Class A/B/C meaning, which largely restates the `settlementClass` enum descriptions; baseline 3 applies.

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 gives a specific verb and resource ('Create an AgentPact v2 intent') and enumerates the three settlement classes, so the agent knows exactly what is produced. It stops short of explicitly distinguishing this from the sibling `create_payment_intent`, which is the most likely confusion point.

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 usefully names a prerequisite path — if no encryption pubkey is registered, call `agentpact.register_encryption_pubkey` and retry — which is real when-to-use guidance. However, it gives no guidance on choosing between this tool and alternatives such as `create_payment_intent`, `propose_deal`, or which settlement class to pick for a given scenario.

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