agent_notifications

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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: the sequence cursor is monotonic, has_room_activity indicates joined rooms changed, has_new indicates an unacked delivery. This goes beyond a generic description and explains the mechanics of the tool.

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 concise, front-loaded with the main purpose, and every sentence provides value. It covers usage, semantics, and alternatives without any fluff.

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?

Despite having only one optional parameter and an output schema, the description fully covers the tool's context: cheap state checks, monotonic cursor semantics, and when to use alternative tools. It is complete for a notification status 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 0%, so the description must compensate for the single parameter 'after_sequence'. It indirectly explains it through 'sequence cursor is monotonic' and 'after the cursor', but does not explicitly state how to use the parameter. Still, the parameter is self-explanatory from context, giving a score of 4.

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 clearly states the tool's function: 'Get durable backlog counts and priorities without loading message bodies.' It uses a specific verb and resource, and explicitly distinguishes itself from siblings by noting it avoids loading message bodies, unlike agent_history or agent_wait.

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 provides explicit when-to-use guidance: 'Use this for cheap state checks or after a listener wake-up.' It also names alternatives and instructions: 'Call agent_wait or paginated agent_history only when needed.' This is clear and actionable.

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