check_messages

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

With no annotations, the description carries the full behavioral burden, and it does not disclose whether 'checking' consumes messages, marks them read, or is an idempotent read. The word 'new' hints at an unread filter but nothing is confirmed. No auth, rate-limit, or state-change context is given.

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?

One front-loaded sentence with no filler, and the scope qualifier ('to this instance') is placed where it counts. It is lean, though slightly under-specified for a tool whose keyword 'Check' carries an ambiguity.

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?

For a zero-parameter tool with an output schema the description need not explain return values, so the remaining requirement is behavioral context. The one sentence leaves the key question unanswered—whether checking mutates read state—which is a meaningful gap given there are no annotations to fall back on.

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?

The tool takes zero parameters and schema description coverage is 100%, so there is nothing for the description to compensate for; baseline 4 applies.

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 clear verb ('Check') and resource ('new messages') with an explicit scope, 'sent to this instance'. This separates it from the sending siblings (send_message, send_room_message) and from room-state tools. It stops short of 5 because 'Check' is ambiguous about whether messages are merely observed or consumed.

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?

There is no guidance on when to use this versus get_room_state, list_participants, or the send_* siblings, and no exclusions or prerequisites. Usage is only implied by the word 'new'.

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