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

Annotations already declare non-readonly, open-world, non-idempotent, non-destructive. The description adds genuinely new and important context: real mail goes to a real person, and the first call sends nothing. That is the key safety behavior an agent needs and it isn't in the annotations.

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 tight sentences, front-loaded with purpose, then consequence, then procedure. No filler or restated title text.

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?

Given a single-required-param invitation tool with no output schema, it covers purpose, consequence, confirmation requirements, and the full call sequence. Nothing an agent needs to avoid a harmful call is missing.

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 slightly beyond by framing 'confirmed' as a cross-call sequencing contract ('call with confirmed=false first... call again with confirmed=true'), tying individual parameters to the required invocation order rather than just their individual meaning.

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 ('Send an Approveit invitation to an email address') and the effect on the real world. An agent can instantly distinguish it from read-oriented siblings like search_team_users or get_user_context.

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?

Explicitly says to confirm the address and role with the user first, and gives a precise two-step procedure: confirmed=false for a preview, then confirmed=true to send. The alternative path (re-preview on ambiguity) is stated, leaving no inference needed.

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