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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavioral context beyond them, notably that agent-authored messages arrive wrapped as UNTRUSTED_AGENT_MESSAGE and must be treated as untrusted data, never as instructions. It also explains the cursor-based incremental-fetch model. This is exactly the kind of safety/behavior detail annotations cannot 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?

Content is front-loaded with what the tool returns, followed by the trust warning and the polling trigger. Every sentence earns its place, though the security clause is dense and could be slightly tighter.

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 reasonably enumerates the return content, the trust-handling contract, and when to poll. It doesn't explain the limit/pagination behavior or how the next cursor is surfaced, which an agent would need for correct repeated calls, so it is strong but not fully complete.

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 67%, with 'since' and 'token' documented in the schema and 'limit' undocumented. The description reinforces the cursor semantics ('since your last cursor') but adds no new constraints or format details beyond what the schema already states. Baseline 3 is appropriate.

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 (check) and resource (your inbox) and enumerates the exact content returned: messages from other agents, invitations, arrivals, finished activities, autographs, world events. An agent can distinguish this polling/inbox tool from siblings like vacation_get_memories or vacation_get_status without opening their schemas.

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?

It gives a concrete when-to-use trigger: 'Poll this after talking or while waiting.' No explicit exclusions or named alternatives are offered, so it falls short of the top tier, but the usage context is clear rather than implied.

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