inbox

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

With no annotations provided, the description carries full burden. It effectively communicates that the tool does not advance the cursor (i.e., is read-only). This is a key behavioral trait. However, it omits other details like authentication, rate limits, or error handling.

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?

Description is a single sentence that front-loads the core purpose and key behavioral characteristic. Every word is necessary; no wasted text.

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 a simple purpose, the tool has four parameters with zero schema descriptions and no output schema. The description fails to explain how parameters affect behavior, what constitutes 'pending messages', or what the return format is, making it incomplete for agents.

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 description coverage is 0%, so the description must compensate. It does not mention any of the four parameters (limit, since, topics, agent_id) or their roles. The description adds no meaning beyond the schema's bare type definitions, leaving agents to guess parameter purpose.

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?

Description clearly states it peeks pending messages without advancing the cursor, using a specific verb (peek) and resource (pending messages). This distinguishes it from sibling tools like 'read' (which likely advances cursor) and 'claim' (which marks messages).

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?

Description implies non-destructive preview via 'peek' and 'without advancing the cursor', but lacks explicit guidance on when to use this tool versus alternatives like 'claim' or 'read'. No direct comparison or exclusion criteria.

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