inbox

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

Explains that reading can mark signals as read, and how to toggle unread_only. However, does not mention side effects of marking read (e.g., state change), or the effect of the 'k' parameter (limit). No annotations to supplement.

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?

Extremely concise: two sentences plus parameter details, no fluff. Front-loads the core purpose effectively.

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?

Adequate for a read tool with parameters, but missing explanation of the 'k' parameter and the nature of 'signals' (whispers/broadcasts). Output schema exists but not described, which is acceptable.

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?

Explains unread_only and mark_read clearly, adding meaning beyond the schema. But fails to describe the 'k' parameter (default 20), which limits result count. Schema coverage is 0%, so description should cover all three parameters.

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?

Describes reading signals addressed to the user (whispers + broadcasts), which is clear and specific. However, it does not explicitly differentiate from other read-related sibling tools like 'brief' or 'notes', but the reference to whispers and broadcasts provides some distinction.

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?

Provides explicit parameter usage: how to use unread_only and mark_read to control behavior. But lacks high-level guidance on when to use this tool vs alternatives (e.g., when to use inbox instead of search or notes).

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