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

The description explicitly states 'WRITES: this call changes stored state and is not safe to repeat blindly,' adding meaningful non-idempotence context beyond the readOnlyHint=false annotation. It does not contradict the annotation. More detail on what state changes occur would raise this further.

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 three sentences with no filler. Each sentence contributes: purpose, parameter-mode guidance, and a mutation warning. The WRITES warning is front-loaded after the core usage, making the structure efficient and scannable.

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?

The description covers the main parameter modes and warns about mutation, but it does not explain the secret parameter, the return value, or what 'lossless per-stream progress' concretely means. Given the complex union type and lack of an output schema, the description leaves some operational gaps.

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?

With schema description coverage at 0%, the description must compensate, and it does meaningfully explain up_to: numeric timestamps versus structured ack_cursor from me(cursor_mode='id'). However, the optional secret parameter is never mentioned, leaving its purpose and source unexplained. This is partial compensation, not complete.

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 opens with 'Advance inbox state,' a clear verb and resource pair that identifies the tool's core purpose. It does not explicitly differentiate from sibling tools like me or me_cadence, though referencing me(cursor_mode='id') hints at its relationship. This is clear but stops short of full sibling contrast.

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?

The description gives concrete invocation guidance: numeric timestamps for the legacy contract and the exact ack_cursor from me(cursor_mode='id') for lossless per-stream progress. It also warns against blind repetition. It does not mention when to prefer this tool over alternatives, so it lacks explicit exclusions.

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