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

Beyond the destructiveHint=true annotation, it discloses the key operational traits: the change takes effect immediately, applies even to a call already waiting, an unnamed agent is barred under 'chosen', and an audit line records the before/after in the company journal. It also notes the owner-only authorization constraint. This is exactly the context annotations cannot convey.

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?

Two compact sentences, front-loaded with the resource and then the mode semantics; nothing is padding. The dense em-dash/parenthetical style (including the PM-1247 ticket reference) makes it slightly harder to scan than it needs to be.

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?

For a destructive two-parameter mutation with no output schema, the description covers authorization, immediacy, in-flight impact, list-replacement semantics and audit trail — everything an agent needs to invoke it safely and 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 baseline is 3, but the description adds real semantics: 'roles' is a full replacement list rather than an additive one ('the whole list — one not named is barred'), and it spells out the practical consequence of 'none'/"all' at the chat level. That goes meaningfully beyond the terse schema strings.

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 ('Choose which agents may be in this company's chats') and immediately enumerates the three policy values, which no sibling does. It is clearly separable from set_chat_agent, set_chat_members and get_chat_agent_policy.

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 explains precisely what each mode means and that 'chosen' requires the 'roles' list, which tells an agent when to pick each option. It stops short of explicitly naming the read counterpart (get_chat_agent_policy) for checking the current setting, so it stops at a strong 4.

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