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

Goes well beyond the readOnly/openWorld annotations: deleted messages are skipped, system events appear as [kind], timestamps use the local time zone, a 20-page x 50-message fetch bound applies, and a truncated:true flag signals an incomplete read. The auth requirement is also disclosed. This is exactly the extra behavioral context annotations cannot carry.

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?

A single tight paragraph, front-loaded with what the tool does before the caveats (deleted messages, timezone, bounds, truncation, auth). Every sentence carries distinct information; nothing is redundant padding.

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 structure need not be explained, and the description still covers ordering, filtering, timezone, pagination bounds, truncation signaling, and account prerequisites. For a read tool of this complexity, an agent has everything needed to call it correctly.

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 100%, so the schema already documents limit, account, and chat_id, putting the baseline at 3. The description adds a little (chat_id provenance, and the 20-page/50-message bound that interacts with limit), but does not add per-parameter syntax or default detail beyond what the schema states.

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 ('Reads the most recent messages of a Microsoft Teams chat'), specifies ordering ('oldest first'), and even points to the source of the required chat_id (teams_list_chats). It implicitly separates chat reads from channel reads, but never explicitly names teams_read_channel_messages or teams_search_messages as alternatives, so sibling differentiation is left to inference.

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?

Gives clear context for use (read recent chat messages, chat_id from teams_list_chats) and a genuine precondition/exclusion: a work or school M365 account must be connected via connect_m365_account, since personal accounts have no Teams reads. It stops short of an explicit 'use X instead when you need Y' routing statement among the read/search siblings.

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