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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the 'Read-only; does not send or change drafts' line is largely redundant. However, the description adds genuinely new behavioral context: drafts expire 30 days after the last save, and the referenced PDF may expire on a separate schedule — expiry semantics the annotations cannot express.

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 the core purpose, then layered with safety, expiry, and disambiguation. The four-item negation list ('quote, approval, payment, or order') is a touch verbose but each clause earns its place by preventing a concrete misuse.

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?

An output schema exists, so return values need not be described, and the safety/expiry picture is solid. The gap is input-side: with zero schema coverage, limit, offset, and the key format are left unexplained, which matters for a paginated list tool.

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 0% across 4 parameters, so the description carries the burden. It gestures at 'matching a label or key', which loosely covers key and query, but says nothing about limit/offset pagination or the key pattern constraint. Two of four parameters remain undocumented anywhere.

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 ('Returns saved correspondence drafts') and adds an explicit negative definition — a draft is not a quote, approval, payment, or order — which routes the agent away from postedly_quote and postedly_orders. The phrase 'matching a label or key' is slightly fuzzy against the actual parameter set (key, query), so it stops short of a 5.

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?

The negative definition ('not a quote, approval, payment, or order') implicitly helps the agent avoid the wrong sibling, but there is no explicit when-to-use statement and no mention of postedly_save_draft or postedly_delete_draft as the write/delete counterparts. Usage is inferable but not stated.

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