Aggregate Recent Teams Messages

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

With no annotations provided, the description carries the full burden. It discloses a key behavioral trait: the resulting messages are 'unread candidates' because Graph lacks a reliable cross-source unread flag. This is honest about the approximation. It does not mention side effects or read-only status, but the main limitation is clearly surfaced.

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 description is concise with two sentences. The first sentence is dense and informative; the second provides Chinese intents, which is useful for multilingual contexts but somewhat redundant for an English-only agent. Overall, it is efficient without unnecessary fluff.

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?

The tool aggregates heterogeneous messages (channels and chats) but has no output schema or annotations. The description does not explain the return format, how 'recent' is defined, or how 'unread candidates' are determined beyond the Graph limitation. This leaves gaps for an agent needing to parse the result or understand the tool's output.

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 only parameter, 'limit', is already well-described in the schema ('Maximum number of message candidates') with 100% coverage. The description does not add any additional param-specific meaning, so it relies on the schema, which is sufficient. A baseline score of 3 is appropriate.

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 action ('Aggregate recent Teams channel and chat messages') and a clear purpose ('as unread candidates'). It distinguishes this from sibling tools like teams_list_channel_messages and teams_list_chat_messages by focusing on cross-source aggregation for unread detection, not just listing 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 description provides clear context by explaining why this tool exists ('Graph does not expose one reliable cross-source unread flag'), implying it is the choice for an aggregated unread view. However, it does not explicitly mention alternatives or exclusion criteria, so it stops short of full usage guidance.

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