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

Annotations already cover the safety profile (readOnly/idempotent/non-destructive), and the description adds substantial context beyond them: Ed25519 request signing, required headers, the reference signer, how to mint a key, and that signing works across both MCP transports with single-use signatures on the SSE channel. This is exactly the auth/behavior detail the annotations cannot convey.

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?

Correctly front-loaded with purpose and paging before the auth block, so the priority order is good. However, the transport paragraph is long and reads like server documentation (SSE query-string details) rather than decision-relevant guidance, diluting conciseness.

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 tool whose hard part is authenticated signing, the description is notably complete: auth, transport, paging, and ordering are all covered. It does not describe the return shape, and with no output schema that is the only remaining gap.

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 'limit', 'before', and 'agent_id' are already documented. The description reinforces the cursor semantics ('before=<next_before>') and result ordering, but adds little beyond what the schema states, so the 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?

States a specific verb and scoped resource: 'YOUR starred messages, newest-starred first.' The ordering and self-scoping distinguish it implicitly from generic message readers like get_agent_inbox and from the write-side star_message. It stops short of naming a sibling alternative explicitly, so it lands at a clear-but-not-fully-differentiating 4.

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?

There is no explicit when-to-use / when-not-to-use statement and no comparison to alternatives such as star_message or get_message. Usage is only implied by the purpose, plus paging guidance ('page back with before=<next_before>'). Adequate but with a clear gap in selection guidance.

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