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

Annotations mark this non-read-only, open-world, non-idempotent with no destructive hint. The description goes well beyond that by disclosing the real-world side effect (this emails a real person), the consent requirement before invocation, and the admin-only authorization gate. That is material behavioral context the annotations alone do not 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?

Front-loaded with the purpose, then the parameter branching, then the safety caveats. Dense and mostly waste-free, though the two trailing caution sentences could be tightened slightly.

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 an action tool with no output schema, the definition covers the identity of the resource, the parameter branches, the side effect, and the consent/authorization gates. Nothing an agent needs to invoke it correctly 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 all three params are already documented. The description restates the same invited_email and context semantics found in the schema, adding only the 'exact address the user gave you' caveat. Baseline 3 is appropriate since the schema carries the burden.

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 (assign) and resource (Policy interview), and clarifies what that means: a Clarity voice interview covering the automation's open Policy questions whose answers are written back onto them. An agent can distinguish this from sibling interview tools like sendClarityInterviewInvites or assignClarityLandscapeCaptureRequest.

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?

Explicit branching guidance: pass invited_email to email someone vs. leave it out for an unassigned slot, plus the selection condition for context. Adds hard preconditions (only after the user says yes, only an address the user gave you, admins and above only), which is exactly the when/when-not info an agent needs.

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