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

With no annotations, the description carries the full burden and does disclose one key behavior: the tool does not send the invitation and only prepares a candidate. It stops short of saying whether the candidate is persisted, returned, or subject to permission checks, which leaves behavioral transparency only partially satisfied.

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 front-loaded sentence contains no filler and immediately communicates the send/no-send distinction. This is appropriately sized for the information it conveys.

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 three-required-parameter tool with no annotations, no output schema, and no property descriptions, the description is insufficient: message is unspecified, target format is unspecified, and the tool's behavior after preparation is unstated. An agent could not reliably populate all required fields.

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 property descriptions are 0%, so the description must supply meaning for target, message, and permissionBasis. It only implicitly covers target/permissionBasis via 'documented machine endpoint or opt-in recipient'; it says nothing about what message should contain, so the agent still lacks needed semantics.

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 names a specific action ('prepare, but do not send'), a concrete resource ('Bursia invitation candidate'), and a target boundary ('documented machine endpoint or opt-in recipient'). It reads clearly, but it does not explicitly contrast any sibling tool, so an agent must infer how it differs from send/policy siblings.

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 phrase 'but do not send' implies this tool is for staging an invitation rather than transmitting it, and the recipient phrase gives a selection criterion. However, there is no explicit when-to-use/when-not-to-use statement or mention of alternatives among the sibling tools.

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