get_new_messages

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

No annotations are provided, so the description carries the burden. It adds the useful behavioral cue that this is a polling-style, presumably non-destructive read operation. However, it does not disclose whether the call marks messages as read, whether it accesses cache or network, or how it behaves with no new messages—important gaps given sibling tools like read_messages and sync_messages.

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 sentence, front-loaded with the core action and filtering condition, plus a concise parenthetical that conveys the intended usage pattern. No wasted words.

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?

Adequate for a simple polling getter: the description plus schema cover what to pass and why. But with no output schema and no annotations, it leaves return-shape expectations and side-effect behavior unstated, and it does not differentiate from closely related siblings such as read_messages, sync_messages, or message_timeline.

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 description coverage is 67%, with since and chat_id described and limit given a default. The description adds no extra parameter semantics beyond 'timestamp' aligning with since's ISO datetime format, so the schema already handles the parameter burden.

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 and resource ('get messages'), a precise selection criterion ('newer than a timestamp'), and the intended use pattern ('polling' for real-time awareness). This clearly distinguishes it from siblings like get_message, read_messages, and search_messages.

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 phrase 'polling pattern for real-time awareness' gives concrete usage context: call repeatedly with a since timestamp to stay current. It does not explicitly name alternatives or say when not to use this tool, but the polling cue is sufficient to orient an agent.

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