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

With no annotations provided, the description carries the full behavioral burden. It discloses important constraints: the invitation is one-use, expires in 48 hours, and is restricted to the room owner. It stops short of describing the response format, but the key behavioral traits are present.

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 with no filler: purpose and constraints are front-loaded, and every sentence contributes either behavioral or security-critical information.

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 simple one-parameter tool with no output schema, the description covers what the invitation is, how long it lasts, who can create it, and how the secret should be handled. It does not explicitly state that the tool returns the secret, but the final sentence implies its existence.

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 schema only provides name/type/format for roomId, and the description adds meaning by implying the room must be owned by the caller and is the target of the invitation. For a single self-explanatory parameter, this is sufficient contextual compensation.

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 clearly states a specific verb ('Create'), a specific resource ('one-use, 48-hour invitation'), and adds unique traits (single-use, expiry, owner-only). This differentiates it from sibling tools like accept_invitation without requiring the reader to inspect schemas.

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?

It gives clear context: the tool should be used by the room owner to invite a specific participant, and the secret should only be shared with that participant. It does not explicitly name alternatives or when-not-to-use scenarios, but the conditions are strong enough to guide selection.

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