inbox

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

No annotations are provided, so the description carries the full burden. It discloses the filtering behavior and the cursor contract, but says nothing about whether reading the inbox consumes/marks messages as read, ordering, or pagination — a critical omission for an inbox-shaped tool.

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?

Two terse sentences with zero waste and the filter condition front-loaded. It is efficient, though the extreme brevity is part of why other dimensions are thin.

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 not be explained. However, with no annotations and an undocumented `limit`, the description leaves the read-vs-consume semantics and cursor mechanics too ambiguous for an agent to invoke this confidently.

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 0%, so the description must compensate. It partially explains `since_id` (messages strictly newer than this cursor) but leaves `limit` (default 50) completely undefined, and does not state whether `since_id` is inclusive or where the next cursor comes from.

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 identifies the resource (messages) and a filter condition (newer than `since_id`), but supplies no verb — it is unclear whether this lists, consumes, or marks messages as read. It also does nothing to distinguish it from sibling `history`, which plausibly returns messages too.

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?

'Keep the cursor between calls' is a useful operational hint about statefulness, but there is no guidance on when to use this over `history`, `room`, or `next_task`, nor any prerequisites. The one hint is procedural, not selection-oriented.

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