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

Annotations already declare readOnlyHint=true, but the description adds real operational context beyond that: the human review URL must not be treated as an approval endpoint, and the lifecycle states (awaiting recipient review, delivery, read confirmation) are explicitly distinguished. That guards against a plausible agent misfire. It omits any mention of polling cadence or state-transition ordering, keeping it short of a 5.

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?

Three short sentences, each carrying distinct information: the read scope, the approval-endpoint caveat, and the state distinction. Front-loaded with the action, no filler, though the second sentence could be tightened slightly.

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 an output schema present, the description needn't enumerate return values, and it correctly focuses on the semantics that matter (the distinct states and the non-approval nature of the review URL). It lacks any guidance on how often to re-check or what to do on each state, which a fully complete definition for a polling tool might include.

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% (draft_id is documented as 'Draft ID returned by federation.messages.draft'), so the single parameter is fully specified by structured data. The description's phrase 'account-owned draft' loosely corroborates that scoping but adds no new syntax or format guidance, so 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?

The description states a specific verb ('Read') and resource ('authoritative account-owned draft and delivery state'), making clear this is a read-only status/state query rather than a draft-creation call. It implicitly separates from the sibling federation.messages.draft, though it never names it or uses the word 'status' explicitly.

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?

Usage is only implied: the warning about the human review URL not being an agent approval endpoint suggests this tool is for polling state while a draft awaits review, but there is no explicit when-to-use or when-not-to-use, nor a pointer to the sibling federation.messages.draft or federation.peers.list as alternatives.

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