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

With no annotations provided, the description must disclose behavioral details itself. It mentions 'since the last read', implying a stateful behavior, but does not explain what happens after reading (e.g., are notes marked as read or deleted?), nor any side effects or authentication requirements. This is a significant gap for a tool that likely mutates read state.

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 a single, front-loaded sentence with no wasted words. It efficiently communicates the primary action and constraint. While it is very short, it is concise for the limited information it provides, though the brevity contributes to incompleteness.

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 read tool with three parameters and no output schema, this description is critically incomplete. It fails to explain parameter semantics, the meaning of 'caller jobs', the output format, or the state transition after read. An agent would struggle to construct a valid call or interpret results correctly.

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?

The description does not explain the purpose of the 'key' and 'name' parameters at all. Only 'ticket' has a schema description, which is terse. Schema coverage is only 33%, and the description adds no meaning beyond the single ticket note. Agents have no clue how to properly identify the mailbox or jobs.

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 'Returns notes left by activity on the caller jobs since the last read' clearly states the action (returns) and resource (notes), and adds a temporal constraint. It is specific enough to understand the basic function, though it does not explicitly differentiate from sibling read tools like deaddrop_read or questions_read.

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?

No guidance is given on when to use this tool versus alternatives, nor are any exclusions or prerequisites mentioned. The description implies it is for reading one's own mailbox but does not clarify the context or alternatives, leaving the agent to infer usage.

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