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

With no annotations, the description carries the full burden and does so richly: it discloses the marking semantics with and without peek, the side effect that messages are kept for older clients, the re-fetch behavior of after=N, paging via more=true, and the SPAKE2 pairing side effect on side A.

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?

It is front-loaded with the most important directive (use the client, not a manual call), but the body is a dense single paragraph of stacked parentheticals that is hard to parse. The content mostly earns its place given the tool's complexity, but the structure could be cleaner.

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 complex, annotation-free tool with no output schema, the description covers return nature (ciphertext), paging, acknowledgment workflow, and the pairing side effect. It is close to complete, with only error/edge-case behavior unaddressed.

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 coverage is 100%, so the baseline is 3, but the description goes beyond the field docs by explaining the default of after (what this side has already fetched), the retry semantics of passing a smaller vs. last-processed N, and the contrast between peek=true and the default marking behavior.

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 and resource: 'Returns the peer's messages this side has not fetched yet,' which is clear and actionable. It also names channel_ack as the downstream sibling, though it does not explicitly contrast itself with channel_send, so sibling differentiation is present but partial.

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?

Explicit when-to-use ('Call only when the person asks'), a stated preferred path (use the local client rather than calling by hand), and a full workflow with alternatives: fetch with peek=true, then channel_ack, and how after=N interacts with reprocessing. This is exactly the when/when-not/alternative guidance expected.

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