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

The description goes beyond the annotations by clarifying the security boundary ('Grants no financial or account authority') and the maximum duration ('up to 7 days'). The readOnlyHint=true annotation aligns with 'prepare owner-signable text,' indicating no state change is committed. It does not deeply explain the signature format or that delegation can be freely reversed, but given the annotations the behavioral posture is reasonably transparent.

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 one well-formed sentence, information-dense, and front-loads the main action ('Prepare owner-signable EIP-191 text'). Every phrase ('presence-only heartbeats', 'up to 7 days', 'no financial or account authority') earns its place and delivers meaningful boundaries.

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 a read-only prepare-purpose, the description covers primary input semantics and the main behavioral constraint. It does not explain defaults or edge cases like what happens when validForHours is omitted, but the output schema can carry the return-value details, and the context is sufficient for an agent to know what is being prepared. A small gap remains around why this versus other delegation counterparts.

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 covers owner and agent as 'EVM address' and tokenId as 'NFH token id', but leaves validForHours without a description. The description compensates by describing the intent: presence-only heartbeats for up to 7 days, which directly explains validForHours in human terms. It does not individually annotate each param, but the semantic gap in the schema is resolved enough.

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 uses a specific verb ('Prepare') plus a concrete resource ('owner-signable EIP-191 text') and defines the delegation scope: 'presence-only heartbeats for up to 7 days.' This is clear enough to distinguish it from generic prepare_* tools, though it does not explicitly name any sibling tool it should be chosen over.

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?

The description implies an obvious use case but gives no explicit guidance on when to choose this tool versus alternatives. The sibling list contains related tools such as prepare_agent_presence and prepare_delegated_agent_heartbeat, and the description does not state the condition that should route an agent away from those. It also does not mention prerequisites, such as needing an owner signature context or the fact that this only prepares a text.

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