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

With no annotations, the description carries the full burden and does disclose the key side effect (messages are marked read unless peek=true) plus a cost of 1 credit per call. It omits other behavioral facts an agent would want, such as whether the read is idempotent or how results are ordered/paginated.

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?

Two tight sentences, front-loaded with the primary inbox action, then the debugging mode, then the cost. Nothing is wasted or repeated from the schema.

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?

For a 5-parameter read with no output schema and no annotations, the description covers both operating modes, the mutation side effect, and cost. It stops short of explaining include_read and limit boundaries, which nothing else documents either.

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 only 40%. The description compensates for 'peek' by explaining it suppresses the mark-as-read side effect, but 'limit' and 'include_read' are undocumented in both the schema and the description, leaving meaningful gaps.

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?

Names the specific resource and the two distinct modes in one breath: reading an agent app's inbox, or the workspace event log. It also states the condition that switches modes (omit 'app'), which is exactly what distinguishes this tool from hub_send, hub_state, and get_audit_log.

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?

Gives clear context for each mode: inbox reading for messages, event log 'for debugging'. It does not explicitly exclude or name alternatives like get_audit_log or hub_state, so an agent must infer routing from names alone.

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