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

Annotations declare non-read-only, idempotent, non-destructive, but the description adds substantial context on top: privacy, request signing via Ed25519 over the handoff-signed-req statement, required headers, key enrollment via `handoff enroll`, and transport-specific nuances (single-use signatures on the SSE bridge that must be re-signed per message, path signed without the ?sessionId query). This is exactly the kind of auth and transport detail annotations cannot carry.

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?

Front-loaded with purpose and default value, then the auth and transport requirements. Every clause is information-bearing, though the transport paragraph is dense and lengthy for a single-flag toggle; it likely belongs in shared auth docs referenced rather than repeated per tool.

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 3-parameter, non-read-only, idempotent tool with no output schema, the description covers everything an agent needs: what it does, the scope restriction, the default, the required signing scheme, header names, how to obtain a key, and per-transport signing caveats. Nothing operational is missing.

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?

With 67% schema coverage, the description reinforces the critical semantic: starred:true is the default and false unstars, which is the whole decision surface for this tool. message_id and agent_id remain thin (agent_id is just 'you' in the schema), but the one ambiguous parameter is fully explained.

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 pair (star/unstar) with the exact parameter value that selects each behavior, and constrains scope to messages the caller can read (sent or received). It also names the underlying HTTP endpoints, making it trivially distinguishable from siblings like list_starred_messages or get_message.

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 clear conditions for use: you may only star messages you can read, and starred:true is the default while starred:false unstars. However, it never names an alternative tool or says when NOT to use this one (e.g., to find starred items use list_starred_messages), so it stops short of full routing guidance.

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