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

Beyond the annotations (readOnly/idempotent/non-destructive/openWorld), the description discloses that pages are live and must be restarted each run, that no auth is needed, that received_elsewhere is a hand-kept list counted in none of the totals, and that the 96-hour answer aim doesn't apply to it. These are meaningful behavioral traits an agent cannot get from the structured fields.

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 core purpose and view semantics are front-loaded, and the operational warnings (live pages, restart each run) are included. It is dense and runs long with some tangential detail (the guest_comment/kind note, 'same contract as GET /api/guest/due'), but nearly every clause carries information the agent needs.

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?

With no output schema, the description carries the return-value burden and does so reasonably: it enumerates the status values, mentions whole-table counts, the last daily-check record, next_cursor paging, and the received_elsewhere block. It is complete enough to call correctly, though it could be more explicit about the shape of the counts.

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 baseline is 3, but the description adds real meaning: it explains the semantics of the two view enum values, that after must come from the SAME view, and implies the page-walking contract for next_cursor. This goes beyond the terse schema strings.

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 states a specific resource (guest critiques the operator's agent aims to answer) and its scope (live status, counts, last daily-check record), and it names the two views. It doesn't explicitly differentiate from siblings like guest_inbox or guest_thread, so an agent must infer the boundary, but the 'due/answer-aim' framing is distinct enough to identify the tool.

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 explains exactly what each view returns and how it is ordered (actionable = open and overdue by due date; history = answered/answered_late/waived by id), which tells the agent when to pick each. It also gives the critical operational rule 'restart from the first page on every run' for live paging. It stops short of naming when to prefer a sibling tool over this one.

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