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

Annotations already declare read-only/idempotent/non-destructive, and the description adds genuinely new behavioral context: the default page size, that `count` is always returned so you are 'never flooded', that reads are never suppressed, that an `unacked_standing_orders` section is conditionally attached, and that bypass_gate is a no-op. This is exactly the extra context the annotations don't 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?

Dense but front-loaded: the default behavior and the flooding guarantee come first, then paging mechanics, then the standing-orders and no-op caveats. Every sentence carries information, though the parenthetical asides and all-caps emphasis make it slightly busier than it needs to be.

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 no output schema, the description carries the return-value burden and does: it names `count` (total in inbox), the newest-last ordering, and the conditional unacked_standing_orders section. Combined with full paging semantics, an agent has everything needed to call and interpret this 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 coverage is 100%, so baseline is 3, but the description adds real meaning beyond the schema: limit:0 fetches the ENTIRE inbox, before returns the window 'ending just before this index', and — importantly — bypass_gate is accepted but a no-op, which refines the schema's own description of that parameter. That no-op disclosure is valuable and earns the bump.

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 ('Retrieve messages from an agent's inbox'), scoping it to a plural, inbox-level read that is clearly distinct from sibling reads like get_message (single) and get_conversation (thread). An agent can pick this out without opening any schema.

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?

Explains the read model in enough depth to drive usage decisions: default of 5 newest messages, how to page with limit/before, and limit:0 to drain the whole inbox. It also routes to ack_standing_orders when the unacked section appears. It stops short of explicit when-to-use/when-not vs sibling reads, so not a 5.

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