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

Annotations only carry generic readOnly/idempotent/destructive hints; the description adds the critical, non-obvious trait that this server never holds keys and never submits, requiring the caller to sign with their own Hedera key, plus the both-sides-setup precondition. It does not explain the non-idempotent flag or any rate/retry behavior, so it stops short of fully rich disclosure.

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?

Four tight sentences, front-loaded with the action and the returned artifact, followed by the signing model and prerequisites. Only the 'it prepares, you sign' clause feels slightly redundant with the preceding sentence, but nothing is wasted.

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?

With no output schema, the description steps up by naming the return value (the exact unsigned payload) and the signing workflow, plus prerequisites and error behavior. Shape of the payload itself is not described, but for a prepare-and-sign tool the agent has what it needs to call 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?

Schema description coverage is 100%, so all three parameters (sender, recipient, text) are already documented, including char limits and the 'no secrets' warning. The description adds no syntax, format, or edge-case detail about the parameters themselves, so the baseline of 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?

States a specific verb and resource ('Prepare an HCS-10 connection request from one agent to another') and elaborates the mechanics: resolves inbound topics and returns an unsigned payload. It is clearly separable from submission-oriented siblings like post_agent_intro because it emphasizes that the server never submits.

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?

Gives a clear prerequisite ('Both agents need completed HCS-10 setup (inbound + outbound topics)') and an error condition ('Honest errors when either side is missing setup'). It does not, however, name an alternative tool or explicitly say when to use a different sibling instead, so it falls short of the 5-level routing guidance.

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