inbox_peek

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

With no annotations, the description carries the full burden and does well: it declares READ-ONLY, states the default payload (body_preview + body_bytes), and flags which behaviors require explicit opt-in. It stops short of describing ordering, pagination, or what 'in-flight' concretely means for a caller.

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?

Three dense clauses with zero filler; the non-consuming read-only framing is front-loaded before the default and opt-in details.

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?

An output schema exists so return values need no explanation, and the description covers the read-only posture, defaults, and opt-ins. It is nearly complete, missing only hints about result ordering/volume expectations.

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 100%, so the schema already documents limit, profile, agent_id, include_bodies and include_parked in detail. The description only restates the include_parked/include_bodies opt-in defaults, adding little beyond the structured fields — the baseline 3 is appropriate.

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?

States a specific verb ('triage/peek') and resource ('pending messages: unread + in-flight') and immediately scopes it as non-consuming, which cleanly separates it from the sibling inbox_pull. An agent can pick this over inbox_pull without opening either schema.

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 when to use it (triage without consuming, envelope-only by default) and notes the opt-in flags for deeper inspection. It never names inbox_pull as the consuming alternative in the description itself, so the when-not is only implied.

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