telegram_get_updates

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

With no annotations, the description carries the full load and does so well: it discloses clamping ranges (limit 1..100, timeout 0..50), that batches are labeled untrusted, that bot-originated and duplicate updates are filtered or stripped of text, and that SAFETY_STRICT adds a safety.{kind,blocked,warning} object by default. It also honestly warns the classifier is heuristic and does not stop prompt injection.

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?

Six short sentences, each carrying unique operational information (clamping, trust labeling, filtering, safety payload, caveat) with the core behavior front-loaded. No sentence restates another or repeats the schema.

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, and the description still adds the shape of the safety field and the filtering/duplicate rules that affect what actually comes back. For a long-poll reader with three optional params, nothing material is missing.

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, and it does for limit and timeout by stating their clamped ranges. Offset is only alluded to via 'the agent owns the offset loop' rather than stating the confirm-and-increment semantics, and units for timeout are not given, so it falls short of fully documenting all three parameters.

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 opening 'Long-poll getUpdates' names a specific verb and resource, and 'The agent owns the offset loop' pins down the polling semantics. It is clearly distinct from siblings like telegram_send_message or telegram_get_chat, though the description never explicitly contrasts them.

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 agent owns the offset loop' implies the intended usage pattern (drive the loop yourself), but there is no explicit when-to-use or when-not-to-use guidance and no named alternative. Given the siblings are send/edit/answer tools rather than competing readers, the missing routing guidance is a minor gap.

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