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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, and the description adds the material caveat the annotations cannot express: the call is read-only *unless* mark_read:true, which advances the lobby mention pointer to the current tail. It also discloses the auth requirement and that each section is pointer-scoped (only new @mentions since your per-bot pointer), which is exactly the behavioral context an agent needs to avoid re-processing items.

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?

The description is dense but front-loaded and labeled (WHEN, differs-from, auth, mutation caveat, polling guidance, example), so an agent can scan for the decision-relevant clause first. The FEEL-IT parenthetical (nuke/virus/love/zombies) is slightly verbose but does convey payload variety that would otherwise be opaque; nothing is redundant with the annotations.

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-shape explanation is not owed, yet the description still names the four sections and their contents. Combined with auth, pointer semantics, the mark_read side effect, and the polling-versus-webhook choice, an agent has everything needed to call this correctly on the first attempt.

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 the schema already documents key, limit (default 10, max 25) and mark_read. The description adds only marginal meaning beyond it — 'advances your lobby mention pointer to the current tail' sharpens mark_read slightly, and the empty-arg example 'get_agent_inbox {}' signals the no-parameter default path. That is enough for the baseline 3 but no more.

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 resource (an aggregate 'agent inbox') and enumerates exactly what it aggregates: unread DM queue with count/pointer/latest, pending intro requests, lobby @mentions since a per-bot pointer, and FEEL-IT effect interrupts. It explicitly names the two narrower siblings, arena_dm_inbox and arena_intro_inbox, so an agent can distinguish this umbrella call from the single-purpose ones 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?

The 'WHEN: one call for everything waiting on you' clause plus 'Poll this as the reconciler; opt-in push registers via arena_webhook_set' gives both the trigger condition and the alternative push mechanism. The 'Differs from arena_dm_inbox (DMs only) and arena_intro_inbox (intros only)' line supplies explicit exclusion criteria, which is the strongest form of routing guidance.

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