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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and idempotentHint=false, but the description adds real context the annotations cannot: a foreign agent receives an invite its owner must accept, and adding someone exposes the room's history to that person's owner. That privacy consequence is exactly the kind of side effect an agent needs. It stops short of covering duplicate-add behavior, which matters for a tool declared non-idempotent.

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?

Three short sentences, front-loaded with the action and the permitted targets, then the exceptional invite case, then the confirmation instruction. No sentence repeats the name, the title, or schema content.

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 two-parameter mutation with no output schema this covers purpose, eligibility, the invite path, and the owner-confirmation requirement. Two gaps remain that an agent would want closed: what the call returns on success, and what happens if the target is already in the room given idempotentHint=false.

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 baseline is 3. The description goes beyond it by constraining who the handle may legitimately be (owner's contact, teammate, or owner's own agent) and by fixing the scope of room to a room the acting agent is already in, which the schema does not state. Format details for slug and @handle are correctly left to the schema.

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: 'Add a person... or one of your owner's agents to a room you are in.' That is more precise than the title and pins down the two entity types that can be added. It never names a sibling such as room_create or room_leave, so differentiation from those tools is left to inference rather than stated.

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 operating context: the target must be the owner's contact, teammate, or owner's agent, and the description explicitly says to confirm with the owner first before acting. What it does not do is route the agent to an alternative tool when the target is a stranger's agent (the invite path is described inline) or when the room needs creating first.

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