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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that the tool reports live or recorded meeting state, whether the bot is still in the lobby, and that it requires the user's Mainroom API key. It does not explicitly say whether it mutates anything, but the 'follow/status' framing strongly implies a read-only observation tool.

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 front-loaded with 'FOLLOW A MEETING' and every clause adds relevant information: what data is returned, how to list sessions, and the required API key. It is somewhat long and dense, but not wasteful given the tool's breadth.

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?

There is no output schema, so the description compensates by enumerating the expected outputs: transcript, summary, answers, decisions, commitments, and lobby status. It also covers authentication and the no-session listing behavior. It lacks format details or error cases, but is sufficient for selecting and invoking the tool 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 description coverage is 100%, so the baseline is 3. The description adds only minor context beyond the schema: it clarifies the relationship to delegate_to_meeting for session ids and repeats the omit-to-list behavior already documented in the session parameter. It does not meaningfully change parameter understanding.

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 opens with a specific verb-resource pair, 'FOLLOW A MEETING', and enumerates exact contents: last transcript lines, running summary, question answers, decisions, commitments, and lobby status. This clearly differentiates it from sibling tools like delegate_to_meeting or join_meeting_as by focusing on observing an agent's live/recorded view of a meeting.

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 gives clear usage context: call with a session id to follow a meeting, or omit it to list recent/live sessions, and notes that session ids come from delegate_to_meeting. It does not explicitly state when not to use this tool or name alternatives, so it stops short of a 5.

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